© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107804
    Prev
    Next
    INDEX
    Explanations

    full article

    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_1_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
    ש
    1.30
    ൈ
    1.27
    ח
    1.24
     dioses
    1.21
    كيف
    1.11
    ু
    1.09
     Balliye
    1.06
     Xinhua
    1.03
    á
    1.02
     profesores
    1.01
    POSITIVE LOGITS
    nie
    1.09
    مع
    1.09
    night
    1.07
    iction
    1.06
    ry
    1.05
    nor
    1.05
    nell
    1.05
    "
    1.04
    ian
    1.03
    ners
    1.01
    Activations Density 0.002%

    No Known Activations