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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 259711
    Prev
    Next
    INDEX
    Explanations

    semicolon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FERC
    1.05
     adapts
    1.04
     aerospace
    1.04
    釭
    1.01
     Adolf
    0.99
     prepares
    0.98
    IOUS
    0.96
     arises
    0.96
     FHWA
    0.96
     contributes
    0.96
    POSITIVE LOGITS
    '
    0.73
    obedience
    0.69
    _
    0.69
    with
    0.68
    that
    0.68
    roly
    0.67
     
    0.67
    several
    0.66
    P
    0.65
    une
    0.65
    Activations Density 0.000%

    No Known Activations