© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104233
    Prev
    Next
    INDEX
    Explanations

    explicitly declares, imports, checks, handles

    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_1_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
    e
    1.29
    c
    1.28
    ،
    1.09
    ：
    1.00
    dang
    0.95
    ED
    0.93
    EDEN
    0.92
     bilgil
    0.91
    _
    0.91
    dauer
    0.89
    POSITIVE LOGITS
     n
    1.26
     is
    1.20
     (
    1.17
    у
    1.17
     t
    1.13
     x
    1.07
    </h2>
    1.06
    ר
    1.05
    (
    1.03
    е
    1.03
    Activations Density 0.012%

    No Known Activations