© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89556
    Prev
    Next
    INDEX
    Explanations

    so then ultimately

    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_11_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
    5
    0.71
     royalty
    0.56
    大
    0.56
     cosplay
    0.56
     cherish
    0.55
     postcard
    0.55
    μία
    0.55
     poppy
    0.54
    ﯽ
    0.54
    incible
    0.54
    POSITIVE LOGITS
     Fractions
    0.65
     Earn
    0.64
    il
    0.63
    ors
    0.62
     Acids
    0.61
     olacaktır
    0.61
    oplasm
    0.61
     fractures
    0.59
     birinci
    0.59
     IDs
    0.59
    Activations Density 0.000%

    No Known Activations