© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11004
    Prev
    Next
    INDEX
    Explanations

    academic text, especially text that refers to processes or officialdom

    oai_token-act-pair · gemini-2.0-flash

    suffixes

    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
    ity
    -0.83
    hip
    -0.77
     autorytatywna
    -0.76
    ment
    -0.67
    Rhestr
    -0.63
    ature
    -0.62
    ceutical
    -0.61
    ary
    -0.60
    ation
    -0.58
    出版年
    -0.58
    POSITIVE LOGITS
    ients
    1.16
    pires
    1.14
    ments
    1.03
    sses
    1.00
    aries
    0.99
    hips
    0.97
    ets
    0.96
    uses
    0.95
    ologies
    0.95
    lines
    0.94
    Activations Density 28.079%

    No Known Activations