© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12528
    Prev
    Next
    INDEX
    Explanations

    internet forum and blog post language

    oai_token-act-pair · gemini-2.0-flash

    hyphens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     PLW
    -0.94
     itſelf
    -0.80
     myſelf
    -0.79
     endregion
    -0.76
    parsedMessage
    -0.76
    xffffffff
    -0.74
     photolibrary
    -0.74
     Eura
    -0.74
    ethene
    -0.73
    onets
    -0.73
    POSITIVE LOGITS
    <bos>
    0.70
    ,
    0.69
     
    0.68
    ’
    0.65
     if
    0.63
    :
    0.58
    -
    0.56
     and
    0.56
    '
    0.56
     clear
    0.54
    Activations Density 1.260%

    No Known Activations