© 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. 134145
    Prev
    Next
    INDEX
    Explanations

    poly[ps, phon, graph, urethane]

    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
    ка
    1.41
    ي
    1.36
    ని
    1.25
    ه
    1.22
    a
    1.18
    dır
    1.17
    া
    1.16
    ك
    1.16
    י
    1.16
     Elektrokh
    1.13
    POSITIVE LOGITS
    il
    1.60
    ene
    1.02
    UT
    0.97
    ul
    0.96
    ερμαν
    0.94
    on
    0.93
    ov
    0.93
    era
    0.93
    وت
    0.89
    ى
    0.89
    Activations Density 0.001%

    No Known Activations