© 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. 158111
    Prev
    Next
    INDEX
    Explanations

    way

    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
    ।
    1.36
    л
    1.30
    。
    1.20
    ні
    1.19
    ،
    1.19
    ла
    1.16
    лі
    1.14
    к
    1.14
    دا
    1.13
    وت
    1.09
    POSITIVE LOGITS
    y
    1.27
    ת
    1.14
     people
    1.02
     a
    1.02
     parasit
    0.95
     X
    0.95
    -
    0.92
     your
    0.91
     cataly
    0.91
     gritty
    0.91
    Activations Density 0.002%

    No Known Activations