© 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. 8847
    Prev
    Next
    INDEX
    Explanations

    a mix of Sanskrit religious terms, diacritics, and words from languages of Eastern Europe

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
     Macau
    -0.40
     pneumonia
    -0.40
    mark
    -0.39
     Munich
    -0.38
     habet
    -0.36
     levier
    -0.35
     Chum
    -0.35
    sui
    -0.35
    win
    -0.35
    ule
    -0.34
    POSITIVE LOGITS
    ngilizce
    0.75
    脚注の使い方
    0.73
     سكانية
    0.69
     فريبيس
    0.68
     Extragalactic
    0.64
     tartalomajánló
    0.63
    abestanden
    0.63
     ويكيپيديا
    0.62
    amse
    0.62
    étit
    0.60
    Activations Density 5.266%

    No Known Activations