© 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. 12996
    Prev
    Next
    INDEX
    Explanations

    legal and programming contexts that contain special characters such as periods, hyphens, underscores, ampersands, parentheses, or single quotes

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash

    punctuation

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     otomatig
    -0.50
    httphttps
    -0.49
    MathML
    -0.49
    tencent
    -0.48
     Illuminate
    -0.47
    män
    -0.47
    complexContent
    -0.47
     cons
    -0.47
     sub
    -0.47
     single
    -0.46
    POSITIVE LOGITS
    rungsseite
    0.66
     BoxFit
    0.59
    Manbalar
    0.58
    TintMode
    0.58
     herzlich
    0.56
    RTEX
    0.56
    Ecotoxicity
    0.54
    ductory
    0.54
     intStringLen
    0.53
    modelBuilder
    0.52
    Activations Density 2.969%

    No Known Activations