© 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. 6631
    Prev
    Next
    INDEX
    Explanations

    words related to permission, rules, and decisions with a negative or questionable connotation.

    oai_token-act-pair · gemini-2.0-flash

    ,

    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
    ^(@)
    -0.90
     Reſ
    -0.84
     Efq
    -0.74
     doubtnut
    -0.73
     pleaſure
    -0.73
     purpoſe
    -0.71
    قایناق‌لار
    -0.70
    mybatisplus
    -0.70
    .*")]
    -0.70
    ſelf
    -0.69
    POSITIVE LOGITS
    save
    0.52
     save
    0.51
     AssemblyTitle
    0.50
    addContainerGap
    0.50
    f
    0.49
    LG
    0.47
    ar
    0.46
    gridy
    0.46
    id
    0.44
    台
    0.44
    Activations Density 4.400%

    No Known Activations