© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 195931
    Prev
    Next
    INDEX
    Explanations

    feature, attribute, step, table

    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_9_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
    d
    1.11
    л
    1.05
    Y
    0.91
    Aren
    0.82
    لنا
    0.79
    HAS
    0.79
    HAD
    0.79
    лло
    0.76
    Coding
    0.75
    the
    0.75
    POSITIVE LOGITS
    iv
    1.05
    يد
    1.04
    ла
    0.89
    od
    0.87
    änen
    0.83
     ört
    0.77
    ا
    0.76
    ificación
    0.74
    ounds
    0.73
    ustrated
    0.73
    Activations Density 0.003%

    No Known Activations