© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151902
    Prev
    Next
    INDEX
    Explanations

    evaluating an answer, often "wrong"

    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_23_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
    rous
    0.38
    rification
    0.34
    sugar
    0.33
    ous
    0.33
    route
    0.33
    🎞
    0.33
    all
    0.32
    ually
    0.32
    er
    0.31
    orage
    0.31
    POSITIVE LOGITS
    КИ
    0.39
     (>
    0.37
     normed
    0.36
     প্রথম
    0.36
    པ
    0.36
    дино
    0.35
     헤
    0.35
     પ્રથમ
    0.35
    大的
    0.35
     अधि
    0.35
    Activations Density 0.001%

    No Known Activations