© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 475
    Prev
    Next
    INDEX
    Explanations

    sports news sources

    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
    讒
    0.41
     ⿻
    0.39
    離開
    0.35
     λ
    0.35
    étrica
    0.35
     ल
    0.35
    に関する法律
    0.34
     lambda
    0.34
    誑
    0.34
     mantras
    0.33
    POSITIVE LOGITS
    Gabriel
    0.40
    Lud
    0.40
    Opera
    0.40
     アクセサリー
    0.39
     Ahmet
    0.39
    Bull
    0.39
    的小
    0.38
    équipe
    0.38
     perforated
    0.37
    的高
    0.37
    Activations Density 0.000%

    No Known Activations