© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199477
    Prev
    Next
    INDEX
    Explanations

    You

    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_50_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
    adım
    0.42
     ریس
    0.41
    hawk
    0.39
    стить
    0.38
    ([-
    0.38
     compré
    0.37
    实
    0.37
    fi
    0.36
     hội
    0.36
    aita
    0.36
    POSITIVE LOGITS
    нена
    0.46
    ंमुळे
    0.41
     dead
    0.38
     Dead
    0.38
     DEAD
    0.37
    Dead
    0.37
    DEAD
    0.35
    gbar
    0.35
     Пере
    0.35
    beren
    0.35
    Activations Density 0.004%

    No Known Activations