© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198270
    Prev
    Next
    INDEX
    Explanations

    numbers after "card", "out", "got", "on"

    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_27_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
     protracted
    0.39
     messing
    0.38
     מו
    0.37
    態
    0.37
     politischen
    0.36
     bunnies
    0.36
     Axes
    0.35
     სახელმწიფო
    0.35
     Verbesserung
    0.35
    克
    0.35
    POSITIVE LOGITS
    utable
    0.32
    compos
    0.32
    uelo
    0.31
    pheromone
    0.31
    istage
    0.30
     joined
    0.30
    joined
    0.30
     rejoined
    0.30
    zIndex
    0.29
     '
    0.29
    Activations Density 0.004%

    No Known Activations