© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205686
    Prev
    Next
    INDEX
    Explanations

    drying out

    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_6_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
    রা
    0.96
    すでに
    0.94
    今まで
    0.94
    να
    0.93
    ad
    0.91
    ൻ
    0.90
    fledged
    0.90
    ONEDB
    0.88
    ap
    0.87
     armament
    0.86
    POSITIVE LOGITS
    ي
    1.79
    i
    1.62
    و
    1.52
    י
    1.51
    IN
    1.34
    ه
    1.26
    lm
    1.21
    ?
    1.21
    ุ
    1.20
    ت
    1.16
    Activations Density 0.000%

    No Known Activations