© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10814
    Prev
    Next
    INDEX
    Explanations

    code snippets related to loading machine learning models, particularly using Keras

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     del
    -0.41
     harmony
    -0.40
     detail
    -0.40
     celu
    -0.38
     i
    -0.36
    AnchorStyles
    -0.36
    nande
    -0.35
     para
    -0.34
     apie
    -0.34
     z
    -0.34
    POSITIVE LOGITS
     Jefus
    1.04
    LookAnd
    0.97
     pleaſure
    0.94
     EconPapers
    0.92
     leaſt
    0.92
     myſelf
    0.91
     متعلقه
    0.90
     purpoſe
    0.88
     Réponses
    0.88
     themſelves
    0.87
    Activations Density 1.036%

    No Known Activations