© 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. 31754
    Prev
    Next
    INDEX
    Explanations

    sources and evidence

    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
     منابع
    0.49
     SOURCES
    0.48
    Sources
    0.45
    -”
    0.44
     Quellen
    0.44
    Referências
    0.42
     sources
    0.42
     Sources
    0.42
    منابع
    0.41
     kaynak
    0.40
    POSITIVE LOGITS
     predator
    0.38
    zigen
    0.38
     吉
    0.38
    ֆ
    0.38
    吉
    0.37
    ForgotPassword
    0.37
     backbone
    0.36
    主力
    0.36
    aints
    0.35
    nash
    0.35
    Activations Density 0.101%

    No Known Activations