© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12061
    Prev
    Next
    INDEX
    Explanations

    information about violent crime

    oai_token-act-pair · gemini-2.0-flash

    violence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     allegedly
    -0.73
    aarrggbb
    -0.71
    SharedDtor
    -0.69
     purported
    -0.60
    OCCURRED
    -0.59
    arean
    -0.59
     reportedly
    -0.58
     supposedly
    -0.57
    IsMutable
    -0.57
     apparently
    -0.57
    POSITIVE LOGITS
     समीक्षाएं
    0.63
    مصادر
    0.55
    Hauptartikel
    0.55
    wok
    0.48
    Lagos
    0.46
    tagHelperRunner
    0.45
    \":\"
    0.45
    /*
    0.45
    /**
    0.45
    lardır
    0.45
    Activations Density 13.080%

    No Known Activations