© 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. 87873
    Prev
    Next
    INDEX
    Explanations

    damage to surfaces, materials, or health

    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
     humor
    0.45
     humorous
    0.42
    UME
    0.41
     जबरदस्त
    0.41
    )²
    0.41
    ERCE
    0.40
     humour
    0.40
     reality
    0.39
     defaults
    0.39
     WASH
    0.38
    POSITIVE LOGITS
    calcul
    0.42
    ကလေး
    0.40
    <unused0>
    0.40
    тивного
    0.40
    鹌
    0.39
     маль
    0.38
    博物館
    0.38
     его
    0.38
    Clk
    0.38
    шко
    0.37
    Activations Density 0.006%

    No Known Activations