© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78811
    Prev
    Next
    INDEX
    Explanations

    most [adjective]

    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_31_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
     +/-
    0.40
     посред
    0.39
     Frank
    0.38
     Affidavit
    0.37
     [{"
    0.36
     Eld
    0.35
     Aff
    0.35
     Edgar
    0.35
     Chairs
    0.35
     조회
    0.34
    POSITIVE LOGITS
    
    0.45
     constantly
    0.40
    (''
    0.39
    ≪
    0.39
    ಂಟು
    0.39
    初めて
    0.38
    ⑷
    0.38
     suficientes
    0.37
    Sustainable
    0.36
    ProjectType
    0.36
    Activations Density 0.013%

    No Known Activations