© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166470
    Prev
    Next
    INDEX
    Explanations

    vital signs

    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_31_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
    Duke
    0.40
    getHours
    0.37
    дзі
    0.36
    Ј
    0.36
     денег
    0.36
    Dyn
    0.36
    Diet
    0.35
    rious
    0.35
    Loren
    0.35
    Toys
    0.35
    POSITIVE LOGITS
     exhib
    0.34
     "__
    0.34
     sele
    0.33
     individui
    0.33
     সর্বনিম্ন
    0.33
     cosecha
    0.33
    最小
    0.33
    astre
    0.32
    十五
    0.32
     Consensus
    0.32
    Activations Density 0.002%

    No Known Activations