© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11009
    Prev
    Next
    INDEX
    Explanations

    words and partial-words that look like parts of names, places, or dates

    oai_token-act-pair · gemini-2.0-flash

    places

    np_max-act-logits · 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
     estekak
    -0.54
    MemoryWarning
    -0.53
    ConstraintMaker
    -0.52
    Jeografia
    -0.51
    RenderAtEndOf
    -0.49
     Fuk
    -0.47
     chng
    -0.47
    şiv
    -0.46
     Similarly
    -0.46
    awm
    -0.45
    POSITIVE LOGITS
     Corsica
    0.50
     Vienne
    0.46
     Florentine
    0.45
     Pyrenees
    0.45
     Flanders
    0.44
    <bos>
    0.43
     Avignon
    0.42
     Italians
    0.42
     Italie
    0.42
     Bacchus
    0.42
    Activations Density 14.681%

    No Known Activations