© 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. 122178
    Prev
    Next
    INDEX
    Explanations

    sonic pi, math, architecture, chemistry

    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
    ない
    0.62
     ممالک
    0.57
    ет
    0.55
    ει
    0.55
     berkel
    0.55
    ஸ
    0.55
     penulis
    0.54
     lineups
    0.53
     seconda
    0.53
     poin
    0.53
    POSITIVE LOGITS
    s
    0.77
    IM
    0.72
    h
    0.71
    IC
    0.67
    g
    0.67
    UN
    0.66
    AR
    0.65
    RA
    0.64
    c
    0.61
    er
    0.61
    Activations Density 0.000%

    No Known Activations