© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13689
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives and positive descriptors

    oai_token-act-pair · gemini-2.0-flash

    After comparatives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     itſelf
    -0.66
     uſ
    -0.61
    ſelf
    -0.57
     Efq
    -0.56
    runApp
    -0.56
     myſelf
    -0.56
     raiſ
    -0.55
     LXXX
    -0.55
    ſelves
    -0.55
    — 
    -0.54
    POSITIVE LOGITS
    ########.
    0.77
    Rüyada
    0.68
     peores
    0.65
    Tikang
    0.60
     확인함
    0.60
    Hentet
    0.59
    rrggbb
    0.58
    MigrationBuilder
    0.57
    TintMode
    0.56
    最快更新
    0.56
    Activations Density 1.968%

    No Known Activations