© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122693
    Prev
    Next
    INDEX
    Explanations

    happen 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_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
     be
    0.76
    K
    0.74
    MUSIC
    0.72
    L
    0.72
    u
    0.71
    s
    0.68
    nią
    0.67
    TING
    0.66
    𝐛
    0.66
    be
    0.66
    POSITIVE LOGITS
     importantes
    0.77
    '
    0.67
    ’
    0.62
     importante
    0.61
     veer
    0.59
    ala
    0.59
    સ
    0.59
     Heidelberg
    0.58
     examin
    0.57
     jett
    0.57
    Activations Density 0.000%

    No Known Activations