© 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. 16313
    Prev
    Next
    INDEX
    Explanations

    words and proper nouns related to drama, interpersonal relationships, and family

    oai_token-act-pair · 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
    LookAnd
    -0.81
    RenderAtEndOf
    -0.75
     المعيارى
    -0.71
    Vidite
    -0.67
     <=",
    -0.62
    styleable
    -0.61
    tinyos
    -0.60
    UnsafeEnabled
    -0.60
     invokingState
    -0.58
    WebMethod
    -0.57
    POSITIVE LOGITS
     Mer
    0.54
    śmy
    0.52
    orian
    0.52
    mybatisplus
    0.51
    ínico
    0.50
    locke
    0.49
    эффици
    0.49
     mer
    0.48
    buro
    0.48
    APTER
    0.47
    Activations Density 5.668%

    No Known Activations