© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17898
    Prev
    Next
    INDEX
    Explanations

    vitamin A derivatives

    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_40_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
     dạy
    0.39
    麥
    0.36
     map
    0.36
     Charger
    0.36
     Jew
    0.36
    idus
    0.35
    麦
    0.35
    вин
    0.35
    টর
    0.34
    dear
    0.34
    POSITIVE LOGITS
    Municipio
    0.41
     淡
    0.41
    ন্ধে
    0.40
     Municipio
    0.40
     municipio
    0.39
    Pos
    0.38
     Pos
    0.38
    ısında
    0.38
     വെള്ള
    0.38
     POS
    0.38
    Activations Density 0.012%

    No Known Activations