© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14149
    Prev
    Next
    INDEX
    Explanations

    bits of code, especially related to networking, memory, or data structures

    oai_token-act-pair · gemini-2.0-flash

    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
    with
    -0.73
    also
    -0.72
    which
    -0.72
    not
    -0.71
    who
    -0.71
    where
    -0.69
    when
    -0.69
    from
    -0.68
    what
    -0.68
    unless
    -0.68
    POSITIVE LOGITS
    ίνεται
    0.47
    +:+
    0.47
    úgó
    0.45
    zulegen
    0.44
    vna
    0.44
    lty
    0.44
    hka
    0.43
    Portale
    0.43
    taire
    0.43
    vede
    0.43
    Activations Density 7.508%

    No Known Activations