© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89216
    Prev
    Next
    INDEX
    Explanations

    folds, stacks, wrinkled surfaces

    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_18_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
    ת
    0.57
    ض
    0.53
    Chief
    0.47
    ש
    0.47
    ל
    0.47
    屑
    0.47
     jour
    0.46
    '
    0.46
    рою
    0.45
    Char
    0.44
    POSITIVE LOGITS
    udahan
    0.49
    <unused338>
    0.47
    вались
    0.47
     anlamına
    0.46
     शकतात
    0.46
     açıklam
    0.45
    டுதல்
    0.44
     પણ
    0.44
     ponerse
    0.43
    atan
    0.43
    Activations Density 0.001%

    No Known Activations