© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175618
    Prev
    Next
    INDEX
    Explanations

    cross-lingual characters

    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_24_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
     substitution
    0.42
     sect
    0.40
    擔
    0.40
    ు
    0.39
     substitu
    0.38
    …
    0.38
    0.38
    ਬ
    0.38
    :-
    0.38
    hore
    0.38
    POSITIVE LOGITS
    ার্জন
    0.51
     බො
    0.47
    amera
    0.46
    RawO
    0.46
    ำ
    0.45
    मेस्टर
    0.44
     '|')
    0.44
    蛳
    0.43
    KU
    0.42
    itabbo
    0.42
    Activations Density 0.000%

    No Known Activations