© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 808
    Prev
    Next
    INDEX
    Explanations

    words that relate to military organization and activity

    oai_token-act-pair · gemini-2.0-flash

    military reconnaissance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     useStyles
    -0.54
     Karol
    -0.54
    orteur
    -0.53
    RenderAtEndOf
    -0.53
    $_['
    -0.51
    UT
    -0.49
    IsMutable
    -0.48
     GoogleFonts
    -0.47
     Buda
    -0.47
     hâte
    -0.46
    POSITIVE LOGITS
     ostavi
    0.65
    esModule
    0.60
     ExecuteAsync
    0.60
    [::-
    0.57
    adpleegd
    0.56
    Pautan
    0.54
     beginnetje
    0.53
    Спасылкі
    0.52
    رشف
    0.52
    Jegyzetek
    0.52
    Activations Density 4.464%

    No Known Activations