© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8526
    Prev
    Next
    INDEX
    Explanations

    technical language related to audio engineering, specifically mentioning "frequencies", "bass", and "filters".

    oai_token-act-pair · gemini-2.0-flash

    specific terms or references related to online sources or entities

    np_token-act-pair-logits · gpt-4o-mini

    sound and music

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zey
    -0.43
     rive
    -0.42
     antiche
    -0.41
    แรง
    -0.37
     الي
    -0.36
    bledon
    -0.36
     concentra
    -0.36
     incubation
    -0.35
    import
    -0.35
    eller
    -0.34
    POSITIVE LOGITS
     Vikipedi
    0.98
    IUrlHelper
    0.90
     EconPapers
    0.89
     pinulongan
    0.82
     المعيارى
    0.79
    HasAnnotation
    0.78
     صوتيه
    0.78
     متعلقه
    0.77
    ftagPool
    0.77
    ngdoc
    0.76
    Activations Density 2.128%

    No Known Activations