© 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. 242929
    Prev
    Next
    INDEX
    Explanations

    game state: false

    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
    νε
    0.44
     \,\
    0.41
     ওঠে
    0.39
    侶
    0.39
     Ago
    0.37
     ascended
    0.37
    છ
    0.37
    वाल
    0.37
     Vorstand
    0.36
    Ago
    0.36
    POSITIVE LOGITS
     porta
    0.43
    ready
    0.42
     siap
    0.40
    unam
    0.39
    readystate
    0.39
     Ready
    0.38
    (.*
    0.37
     Repair
    0.37
     repar
    0.36
    ítom
    0.36
    Activations Density 0.002%

    No Known Activations