© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25071
    Prev
    Next
    INDEX
    Explanations

    word endings

    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_10_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
    ک
    0.80
    V
    0.79
    P
    0.76
    K
    0.75
    M
    0.74
    H
    0.74
    ants
    0.73
    К
    0.73
    C
    0.70
    ushes
    0.70
    POSITIVE LOGITS
     etti
    0.70
     người
    0.63
     đau
    0.62
     THAT
    0.60
     gé
    0.59
    다
    0.58
     في
    0.57
    ição
    0.55
     tôi
    0.55
     disciple
    0.54
    Activations Density 0.025%

    No Known Activations