© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234067
    Prev
    Next
    INDEX
    Explanations

    rust code imports

    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_32_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
    Scottish
    0.41
     Scottish
    0.39
     padd
    0.37
    һ
    0.37
    笞
    0.36
     Frederic
    0.36
     gỗ
    0.34
     motors
    0.33
     pulang
    0.33
     \%$
    0.33
    POSITIVE LOGITS
    oper
    0.41
     εξα
    0.39
     საკ
    0.38
     operativos
    0.36
    ]::-
    0.35
    敢
    0.35
     ongles
    0.35
    ഭ്യാസ
    0.35
    tere
    0.35
     operative
    0.35
    Activations Density 0.001%

    No Known Activations