© 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. 201771
    Prev
    Next
    INDEX
    Explanations

    items for sale

    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
    ра
    0.95
    diagonal
    0.89
    g
    0.89
    гуу
    0.87
    ס
    0.87
    gkin
    0.81
    ின்
    0.80
    ﺪ
    0.80
    𝗱
    0.78
     بیٹھ
    0.77
    POSITIVE LOGITS
    <0x0D>
    1.30
     A
    1.27
     Y
    1.20
     N
    1.13
     X
    1.12
     P
    1.11
     I
    1.10
     R
    1.09
     T
    1.07
     F
    1.05
    Activations Density 0.059%

    No Known Activations