© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258691
    Prev
    Next
    INDEX
    Explanations

    json configuration

    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_22_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
    ufer
    0.45
     pfl
    0.45
     ಇದಕ್ಕೆ
    0.44
    孤
    0.44
    ью
    0.44
     поверхность
    0.43
    病的
    0.42
    스럽
    0.41
    nath
    0.41
     henry
    0.41
    POSITIVE LOGITS
    :'
    0.47
     '
    0.45
    ́
    0.41
    aaa
    0.39
    }-
    0.38
    aaaa
    0.38
     Namely
    0.38
     Hygiene
    0.38
    ́t
    0.38
    annies
    0.37
    Activations Density 0.000%

    No Known Activations