© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4564
    Prev
    Next
    INDEX
    Explanations

    quality descriptors

    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_39_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
     *
    0.35
     Oceans
    0.35
    OTH
    0.33
     '
    0.32
     insign
    0.31
     अमा
    0.31
     `
    0.31
    Icons
    0.31
     "+
    0.31
     ....
    0.30
    POSITIVE LOGITS
     கிஷோர்
    0.43
     vapour
    0.40
     جميل
    0.36
     zombie
    0.35
     Heming
    0.35
    আনু
    0.35
     Persever
    0.34
    yson
    0.34
    앙
    0.34
    homotopic
    0.33
    Activations Density 0.016%

    No Known Activations