© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53279
    Prev
    Next
    INDEX
    Explanations

    opened and actions

    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_31_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
     COMPOUNDS
    0.30
     CRE
    0.29
    냐
    0.29
    cssMode
    0.28
     Cre
    0.28
    ㎞
    0.28
     Gro
    0.28
     stran
    0.28
    ന്യ
    0.27
     desvent
    0.27
    POSITIVE LOGITS
    ueel
    0.32
    psr
    0.31
    »:
    0.30
    пс
    0.30
    ͤ
    0.29
    YB
    0.28
    attere
    0.28
    ibb
    0.28
    otele
    0.28
    ė
    0.28
    Activations Density 0.005%

    No Known Activations