© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11252
    Prev
    Next
    INDEX
    Explanations

    words about topics being discussed or feelings.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Day
    -0.96
    Day
    -0.94
     برانيه
    -0.89
    Almost
    -0.88
     Almost
    -0.84
     DAY
    -0.74
    almost
    -0.72
    verwijspagina
    -0.69
    day
    -0.68
     All
    -0.68
    POSITIVE LOGITS
    DrawerToggle
    0.67
    Uninitialized
    0.56
    cerpts
    0.56
    atigable
    0.53
    ectl
    0.51
    eabouts
    0.50
    ścić
    0.47
    whence
    0.47
    glyphicon
    0.46
    virons
    0.46
    Activations Density 26.135%

    No Known Activations