© 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. 13944
    Prev
    Next
    INDEX
    Explanations

    default manifest

    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
    逄
    0.40
    oster
    0.39
    ที่สุด
    0.39
    iries
    0.38
    Wendy
    0.38
     poset
    0.38
    方位
    0.37
    χος
    0.37
    Decedent
    0.36
     Wendy
    0.36
    POSITIVE LOGITS
     scram
    0.41
     "$
    0.38
     Verm
    0.37
     technically
    0.36
     erk
    0.36
     getY
    0.36
     verm
    0.34
     recognises
    0.34
    ループ
    0.34
     ""),
    0.33
    Activations Density 0.008%

    No Known Activations