© 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. 5988
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with legal complaints that involve damage and monetary compensation.

    oai_token-act-pair · gemini-2.0-flash

    giving advice

    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
    ห์
    -0.46
    WriteLiteral
    -0.45
    +</
    -0.41
     Ciencia
    -0.41
     OnInit
    -0.41
    AndEndTag
    -0.40
    ViewInit
    -0.40
    onOptions
    -0.40
     gustado
    -0.39
    Rage
    -0.39
    POSITIVE LOGITS
     advised
    1.88
     advise
    1.85
     advises
    1.61
    advised
    1.55
     advising
    1.55
     advice
    1.35
     ADVIS
    1.34
    advice
    1.30
     Advice
    1.28
     ADVICE
    1.18
    Activations Density 11.890%

    No Known Activations