© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204907
    Prev
    Next
    INDEX
    Explanations

    Spanish math and explanations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     ent
    0.41
     Executives
    0.41
    র্ঘ
    0.39
    .--
    0.39
    uyến
    0.37
    --");
    0.37
    .~
    0.35
    アダ
    0.35
     LORD
    0.35
     Ya
    0.35
    POSITIVE LOGITS
     oper
    0.44
     «
    0.42
     X
    0.40
     Den
    0.40
    X
    0.40
     burying
    0.40
     potencial
    0.40
     arent
    0.40
     »
    0.39
    Den
    0.39
    Activations Density 0.000%

    No Known Activations