© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15934
    Prev
    Next
    INDEX
    Explanations

    legal language including clauses, conditions, requirements, and numbered lists

    oai_token-act-pair · gemini-2.0-flash

    semicolon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    __':
    -0.82
    ⓧ
    -0.81
     myſelf
    -0.75
     Efq
    -0.74
     Majefty
    -0.74
     itſelf
    -0.73
     pleaſure
    -0.72
     Monfieur
    -0.71
     Jefus
    -0.71
     Forumite
    -0.71
    POSITIVE LOGITS
     and
    0.75
    ↵↵
    0.62
     It
    0.58
     The
    0.58
     all
    0.58
     an
    0.57
     This
    0.56
     it
    0.56
     I
    0.54
    </strong>
    0.54
    Activations Density 20.260%

    No Known Activations