© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4743
    Prev
    Next
    INDEX
    Explanations

    the word "form", sometimes but not always in the context of paperwork.

    oai_token-act-pair · gemini-2.0-flash

    form

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    MigrationBuilder
    -0.72
    MENAFN
    -0.66
    ItemBackground
    -0.62
    ########.
    -0.57
     fiscales
    -0.55
     ferroviaire
    -0.54
    Form
    -0.54
     kartą
    -0.50
    quelize
    -0.50
    /******/
    -0.50
    POSITIVE LOGITS
    ulates
    0.58
    ulir
    0.50
    ulate
    0.50
    alised
    0.49
     Ро
    0.49
    AutoScaleMode
    0.49
    ulated
    0.48
    dehyde
    0.47
     annehmen
    0.47
    ulas
    0.47
    Activations Density 1.068%

    No Known Activations