© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216035
    Prev
    Next
    INDEX
    Explanations

    python test methods

    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
     كور
    0.41
     တယ်
    0.41
    काउंट
    0.40
    GQ
    0.40
    媜
    0.40
     кор
    0.39
    調查
    0.39
     sostegno
    0.38
     pauses
    0.38
     గో
    0.38
    POSITIVE LOGITS
    och
    0.41
    generated
    0.40
    arg
    0.38
    bers
    0.38
    ous
    0.37
    ся
    0.36
    gs
    0.36
    ⊔
    0.36
    ously
    0.36
     burn
    0.36
    Activations Density 0.001%

    No Known Activations