© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18728
    Prev
    Next
    INDEX
    Explanations

    entities and groups

    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_15_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
    INES
    0.33
    ETIC
    0.33
    校
    0.32
    多个
    0.31
    ERON
    0.31
     பகுதி
    0.31
    ERO
    0.31
    τού
    0.31
    ITO
    0.30
    형
    0.30
    POSITIVE LOGITS
     samme
    0.33
     samma
    0.33
     relegated
    0.32
    ’
    0.32
     connexes
    0.32
     isomorphic
    0.31
     enthusiasts
    0.31
     similaires
    0.31
     McKinsey
    0.30
    /).
    0.30
    Activations Density 0.089%

    No Known Activations