© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162678
    Prev
    Next
    INDEX
    Explanations

    encoding, charset, HTTP, US

    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_31_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
     remplacement
    0.41
    骢
    0.37
    纹
    0.36
     replacement
    0.36
     mouths
    0.36
     zaji
    0.36
    Replacement
    0.36
    र्ज
    0.35
     remplacer
    0.35
    長く
    0.35
    POSITIVE LOGITS
    యితే
    0.37
     mitig
    0.37
     регла
    0.35
     olay
    0.35
     Chilton
    0.35
    يكية
    0.35
    움
    0.35
     Packet
    0.34
     Carbon
    0.34
     citation
    0.33
    Activations Density 0.000%

    No Known Activations