© 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. 11333
    Prev
    Next
    INDEX
    Explanations

    calls to action involving clicking a link

    oai_token-act-pair · gemini-2.0-flash

    Click

    np_max-act-logits · 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
     auroit
    -0.71
     perfons
    -0.69
     itſelf
    -0.68
    IContainer
    -0.66
     Efq
    -0.66
     moſt
    -0.65
    rungsseite
    -0.65
     enfans
    -0.63
     feroit
    -0.63
    enapa
    -0.63
    POSITIVE LOGITS
    y
    0.63
    /
    0.55
    ure
    0.54
     the
    0.52
    er
    0.52
     sign
    0.49
    ing
    0.49
     &
    0.45
    ant
    0.45
    SequentialGroup
    0.44
    Activations Density 4.854%

    No Known Activations