© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56808
    Prev
    Next
    INDEX
    Explanations

    Indus Valley Civilization

    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_11_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
    ITLE
    0.45
    び
    0.44
    ---’
    0.43
    ৤
    0.43
    ほう
    0.43
     शिक्षक
    0.42
    的な
    0.41
    LETE
    0.41
    то
    0.41
    名を
    0.41
    POSITIVE LOGITS
    N
    0.57
    L
    0.49
    చ్
    0.48
     man
    0.48
    ജ
    0.47
    })(\
    0.46
     of
    0.46
     L
    0.45
    }\
    0.45
     Cenomanian
    0.45
    Activations Density 0.007%

    No Known Activations