© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24402
    Prev
    Next
    INDEX
    Explanations

    bulk issuance

    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_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
     as
    0.86
    <0x0D>
    0.81
    ף
    0.79
    q
    0.77
    ling
    0.76
     and
    0.75
     You
    0.74
     \
    0.72
    w
    0.72
    其
    0.72
    POSITIVE LOGITS
     bulk
    0.77
    fdPar
    0.73
    თა
    0.72
    тта
    0.72
    ́c
    0.72
    тік
    0.70
    იშ
    0.69
    the
    0.68
    ков
    0.66
    testAvg
    0.66
    Activations Density 0.005%

    No Known Activations