© 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. 31063
    Prev
    Next
    INDEX
    Explanations

    task:

    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
     lente
    0.37
    泹
    0.37
    impse
    0.37
    itekt
    0.37
    ૈય
    0.35
     jõ
    0.35
    āv
    0.35
     reactants
    0.35
     southernmost
    0.35
    埚
    0.34
    POSITIVE LOGITS
     giving
    0.44
    Salmon
    0.43
     разре
    0.40
     reluctantly
    0.38
     요구
    0.38
    centric
    0.38
     tiện
    0.37
    give
    0.37
     skup
    0.37
    andaş
    0.37
    Activations Density 0.006%

    No Known Activations