© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41687
    Prev
    Next
    INDEX
    Explanations

    balazuc, balinese, mahabaleshwar, pascal

    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_3_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
    ates
    0.66
    と
    0.63
    篂
    0.60
    과
    0.59
    捙
    0.59
    }></
    0.58
    鿆
    0.58
     اور
    0.57
    aches
    0.57
    သည်။
    0.57
    POSITIVE LOGITS
    n
    1.08
    z
    1.04
    b
    1.01
    v
    1.01
     $
    0.92
    ק
    0.90
    x
    0.83
    is
    0.82
    l
    0.77
    ע
    0.77
    Activations Density 0.006%

    No Known Activations