© 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. 123044
    Prev
    Next
    INDEX
    Explanations

    OSASCOMP, o, os, osaki, osl

    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
    ور
    0.92
    еры
    0.71
    حة
    0.66
     fifties
    0.60
    <0x80>
    0.60
    ách
    0.60
     unbear
    0.59
    urra
    0.59
     thirties
    0.59
     significado
    0.58
    POSITIVE LOGITS
    は
    0.95
    न
    0.87
    ।
    0.83
    는
    0.81
    .
    0.77
    NO
    0.76
    𝟰
    0.76
    }.
    0.76
    ה
    0.75
    SDK
    0.74
    Activations Density 0.000%

    No Known Activations