© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35996
    Prev
    Next
    INDEX
    Explanations

    scorecard

    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_3_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
    ด์
    0.78
    that
    0.78
    t
    0.76
    an
    0.75
    at
    0.74
     that
    0.72
    US
    0.71
    dır
    0.68
    지에
    0.65
    지
    0.65
    POSITIVE LOGITS
     scor
    0.80
     إ
    0.77
     \
    0.74
     կ
    0.72
     оружи
    0.72
    ме
    0.71
    ٻ
    0.71
    ově
    0.70
     score
    0.69
     activid
    0.68
    Activations Density 0.001%

    No Known Activations