© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4024
    Prev
    Next
    INDEX
    Explanations

    lines of text, particularly those starting with "line"

    oai_token-act-pair · gemini-2.0-flash

    line

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     setuptools
    -0.63
    tagHelperRunner
    -0.58
    Seats
    -0.52
     Charters
    -0.52
     rác
    -0.52
    Timed
    -0.52
    Carriera
    -0.51
    ness
    -0.50
    seamless
    -0.50
     Compressed
    -0.50
    POSITIVE LOGITS
    mybatisplus
    0.51
    DeleteBehavior
    0.51
    parseColor
    0.49
     autorytatywna
    0.49
    nikova
    0.48
    شتی
    0.47
    mergeFrom
    0.47
    +#+
    0.46
    ISTRATION
    0.46
    ährung
    0.45
    Activations Density 5.004%

    No Known Activations