© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13968
    Prev
    Next
    INDEX
    Explanations

    research funding and organization names, especially Dutch ones

    oai_token-act-pair · gemini-2.0-flash

    lijk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     محفوظة
    -0.99
    
    -0.90
     دیکھیے
    -0.88
    StructEnd
    -0.81
     Efq
    -0.79
    daß
    -0.78
    bibinfo
    -0.77
     متعلقه
    -0.76
     itſelf
    -0.76
    aspectj
    -0.75
    POSITIVE LOGITS
    ver
    0.46
    вер
    0.37
     van
    0.37
     kon
    0.37
     pro
    0.36
    旅
    0.35
     da
    0.35
    valho
    0.35
     vor
    0.35
    bas
    0.35
    Activations Density 0.178%

    No Known Activations