© 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. 12401
    Prev
    Next
    INDEX
    Explanations

    abbreviations or short alphabetic codes that sometimes represent locations

    oai_token-act-pair · 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
    for
    -1.01
    from
    -1.00
    and
    -0.96
    to
    -0.90
    of
    -0.86
    with
    -0.84
    that
    -0.81
    which
    -0.71
    the
    -0.71
    if
    -0.70
    POSITIVE LOGITS
     that
    0.70
     if
    0.69
     of
    0.68
     the
    0.67
     in
    0.66
     they
    0.66
     with
    0.65
     he
    0.65
     or
    0.65
     to
    0.64
    Activations Density 7.623%

    No Known Activations