© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12991
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with talking, truth, or the heart

    oai_token-act-pair · gemini-2.0-flash

    Conversations and personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Normdatei
    -0.59
     nela
    -0.57
     pessoais
    -0.53
    Jeografia
    -0.51
     Felsen
    -0.51
     alugar
    -0.50
    UrlResolution
    -0.49
    providedIn
    -0.49
    المكان
    -0.48
     émotion
    -0.48
    POSITIVE LOGITS
     مشين
    0.68
    وبة
    0.57
     invokingState
    0.55
    adaptiveStyles
    0.55
    lieg
    0.54
    WithIOException
    0.54
    QPalette
    0.52
    @[+][
    0.52
    ParallelGroup
    0.51
    ([
    0.51
    Activations Density 1.490%

    No Known Activations