Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165931
    Prev
    Next
    INDEX
    Explanations

    hosts, ice cream, period, purple

    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_13_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
    v
    0.62
    ステ
    0.49
     Schwester
    0.49
     sveta
    0.49
    -
    0.49
    olve
    0.48
     egos
    0.45
    り
    0.45
     জড়
    0.44
     nejsou
    0.44
    POSITIVE LOGITS
     Niveau
    0.42
    чик
    0.41
    ಾವಣ
    0.41
     Bugs
    0.41
    兗
    0.41
    дання
    0.41
     MMR
    0.41
     bullish
    0.41
     PACK
    0.40
    ophan
    0.40
    Activations Density 0.000%

    No Known Activations