© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60210
    Prev
    Next
    INDEX
    Explanations

    corrected code and spelling

    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_2_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
     שה
    1.15
    .
    1.02
    Р
    0.96
     that
    0.96
     אי
    0.92
     αλλά
    0.90
     కానీ
    0.89
     ваших
    0.88
     Ар
    0.88
     astonished
    0.87
    POSITIVE LOGITS
    it
    1.38
    ä
    1.20
    a
    1.11
    and
    1.07
     It
    0.96
    f
    0.89
    ো
    0.89
    t
    0.89
    ून
    0.86
    ag
    0.84
    Activations Density 0.001%

    No Known Activations