© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59305
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ре
    1.38
    ಾ
    1.30
    ா
    1.23
    ри
    1.19
    ू
    1.16
    he
    1.16
    ла
    1.16
    да
    1.13
    на
    1.08
    ান
    1.07
    POSITIVE LOGITS
     (
    1.42
    س
    1.31
    -
    1.29
    S
    1.26
    s
    1.17
    a
    1.11
    A
    1.09
    M
    1.09
    ه
    1.07
    EP
    1.03
    Activations Density 0.000%

    No Known Activations