© 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. 8500
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with fantastical and surreal literature

    oai_token-act-pair · gemini-2.0-flash

    fictional and mythical narratives

    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
    KEYCODE
    -0.59
    GraphicsUnit
    -0.55
     nakalista
    -0.54
    <bos>
    -0.52
    antren
    -0.50
    IsContent
    -0.49
    показания
    -0.47
    ♂
    -0.47
     utafitiHapana
    -0.47
    mobileqq
    -0.46
    POSITIVE LOGITS
     nahilalakip
    0.91
     lenker
    0.55
     fantastic
    0.54
    crí
    0.54
    fantastic
    0.53
    NewGuid
    0.52
    cdnjs
    0.50
    readdir
    0.49
    simpleType
    0.49
    LayoutPanel
    0.48
    Activations Density 7.274%

    No Known Activations