© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10138
    Prev
    Next
    INDEX
    Explanations

    part-time/full-time

    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_13_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
     restraint
    0.47
     reciprocating
    0.44
     braking
    0.41
     commencent
    0.41
     restraining
    0.40
    셩
    0.40
    այի
    0.40
    ◝
    0.39
     columnas
    0.39
    シート
    0.39
    POSITIVE LOGITS
    ว
    0.47
     .
    0.44
    Nintendo
    0.44
    Halloween
    0.43
    ?
    0.43
     -
    0.42
    im
    0.42
    ון
    0.42
    ודי
    0.42
    ल
    0.41
    Activations Density 0.004%

    No Known Activations