© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249161
    Prev
    Next
    INDEX
    Explanations

    actresses

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     who
    0.59
    谁
    0.52
    who
    0.50
     quien
    0.47
     whos
    0.45
    Who
    0.44
     Who
    0.44
     quién
    0.43
    誰
    0.43
     siapa
    0.42
    POSITIVE LOGITS
    vom
    0.38
    忝
    0.37
    ాలతో
    0.36
    കൊ
    0.36
    optimize
    0.35
     Liter
    0.34
     Vom
    0.34
     diventa
    0.34
     основним
    0.34
    Sizes
    0.34
    Activations Density 0.002%

    No Known Activations