© 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. 38340
    Prev
    Next
    INDEX
    Explanations

    South India and directions

    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
    ו
    0.62
    ет
    0.57
     diga
    0.56
     ajudar
    0.55
     angu
    0.55
     affixed
    0.55
    }
    0.55
     industrious
    0.54
    ")
    0.54
    ти
    0.54
    POSITIVE LOGITS
    iere
    0.71
    יות
    0.66
    as
    0.63
    ページ
    0.61
    ך
    0.61
    machines
    0.59
    يّ
    0.59
    is
    0.59
    urt
    0.59
    slope
    0.59
    Activations Density 0.001%

    No Known Activations