© 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. 5910
    Prev
    Next
    INDEX
    Explanations

    text related to app development, coupons, and shopping

    oai_token-act-pair · gemini-2.0-flash

    Incomplete sentences/content

    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
    __;
    -0.65
    Acest
    -0.54
    ')):
    -0.51
    _
    -0.50
    Tembelea
    -0.50
    protoimpl
    -0.49
    '));
    -0.47
     yyl
    -0.47
    )");
    -0.47
    **
    -0.46
    POSITIVE LOGITS
    脚注の使い方
    0.77
    DockStyle
    0.66
     quæ
    0.58
     وتسجيلات
    0.58
     propOrder
    0.56
    
    0.54
     Walkover
    0.54
    tvguidetime
    0.52
    timewa
    0.52
    verläs
    0.52
    Activations Density 18.342%

    No Known Activations