© 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. 42291
    Prev
    Next
    INDEX
    Explanations

    EMIEW, EM001, EMP002, Em7, emogis

    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
    ’
    0.73
     profiter
    0.73
    స్
    0.70
    ش
    0.69
     truck
    0.66
     neben
    0.64
     investi
    0.63
    ür
    0.62
     wetter
    0.62
    ت
    0.62
    POSITIVE LOGITS
    x
    0.78
    y
    0.75
    d
    0.74
    dSample
    0.71
    represents
    0.71
     आंकड़ों
    0.68
    _*
    0.67
    もの
    0.66
    '[
    0.66
    dependent
    0.65
    Activations Density 0.010%

    No Known Activations