© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43258
    Prev
    Next
    INDEX
    Explanations

    Lochner Era lessons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    ar
    1.45
    t
    1.42
    n
    1.19
    as
    1.04
    ان
    1.02
    en
    0.99
    il
    0.98
    it
    0.98
    os
    0.98
    un
    0.95
    POSITIVE LOGITS
    _
    0.93
    of
    0.93
    ]){
    0.73
    with
    0.69
    OF
    0.66
    (
    0.66
    ني
    0.66
    ০
    0.65
     of
    0.65
    的女
    0.65
    Activations Density 0.002%

    No Known Activations