© 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. 123317
    Prev
    Next
    INDEX
    Explanations

    Investigation, burst, swell, Jr, Kitchen, Pand

    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
    ’
    0.84
    ।
    0.79
    ox
    0.79
    FU
    0.75
    dV
    0.74
    dalam
    0.73
    dokument
    0.73
    d
    0.72
    dans
    0.71
    discussion
    0.70
    POSITIVE LOGITS
    ยุ
    0.70
     pouvoir
    0.66
     aerospace
    0.64
     apresent
    0.63
     enfoque
    0.63
     inclu
    0.60
     progrès
    0.60
     acreditar
    0.59
    ฝึก
    0.59
     be
    0.59
    Activations Density 0.001%

    No Known Activations