© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96623
    Prev
    Next
    INDEX
    Explanations

    exciting, taste, bliss

    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_14_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
    on
    0.19
    is
    0.18
    ográfico
    0.17
     мечта
    0.16
     écrite
    0.15
     hommage
    0.15
     découvre
    0.15
    ++];
    0.14
    ز
    0.14
     réuss
    0.14
    POSITIVE LOGITS
    Time
    0.19
    Analytical
    0.18
    Α
    0.18
    OU
    0.17
    ENTE
    0.17
    Guid
    0.17
    АТ
    0.17
    Unexpected
    0.17
    Karena
    0.16
    А
    0.16
    Activations Density 0.008%

    No Known Activations