© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11334
    Prev
    Next
    INDEX
    Explanations

    the form feed character.

    oai_token-act-pair · gemini-2.0-flash

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    HINT
    -0.60
    theit
    -0.60
     original
    -0.60
    UGHS
    -0.59
     copia
    -0.59
    ParallelGroup
    -0.58
    läg
    -0.55
    ICION
    -0.54
    diğinde
    -0.54
     ngh
    -0.52
    POSITIVE LOGITS
    <bos>
    1.25
    /*
    0.84
    Personensuche
    0.82
    setVerticalGroup
    0.74
    хьтан
    0.71
    Parcelize
    0.71
     ModelExpression
    0.70
    WriteTagHelper
    0.69
     doInBackground
    0.69
     архивлан
    0.68
    Activations Density 1.676%

    No Known Activations