© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146177
    Prev
    Next
    INDEX
    Explanations

    scientific names

    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_59_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
     Crab
    0.44
     crab
    0.41
     Fly
    0.40
     scram
    0.40
    找
    0.39
     clam
    0.39
     Crank
    0.39
    蟹
    0.39
     crustaceans
    0.39
    crab
    0.38
    POSITIVE LOGITS
    गुरु
    0.38
    african
    0.38
    gboost
    0.37
     african
    0.37
     investigator
    0.36
    美好的
    0.36
     *);
    0.36
     commens
    0.35
    츰
    0.35
    Morgan
    0.35
    Activations Density 0.003%

    No Known Activations