© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36200
    Prev
    Next
    INDEX
    Explanations

    curl or png

    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
    ’
    0.68
     opponents
    0.61
     هاي
    0.59
     serii
    0.58
    ni
    0.54
     on
    0.52
    坤
    0.52
     automaker
    0.52
     grandchildren
    0.51
    ERRY
    0.51
    POSITIVE LOGITS
    O
    0.96
    A
    0.82
    I
    0.80
    ویت
    0.64
    ه
    0.60
    آمد
    0.59
    E
    0.59
    ל
    0.59
    ционе
    0.58
    ر
    0.58
    Activations Density 0.002%

    No Known Activations