© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157950
    Prev
    Next
    INDEX
    Explanations

    sickeningly

    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_2_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
    ام
    1.23
    د
    1.18
    ان
    1.14
    ب
    1.12
    ه
    1.11
    ਾ
    1.04
    in
    1.00
    gehend
    0.98
    imbo
    0.98
    هم
    0.98
    POSITIVE LOGITS
    -
    1.17
    ii
    1.09
     l
    0.96
     ropa
    0.96
     financière
    0.96
    ix
    0.95
     danni
    0.93
     física
    0.93
     algorit
    0.93
    m
    0.93
    Activations Density 0.000%

    No Known Activations