© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219426
    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_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
     kü
    0.38
     corresponding
    0.35
     forward
    0.35
     Corresponding
    0.35
    forward
    0.35
    corresponding
    0.35
    ",&
    0.34
    IBILITY
    0.34
    呐
    0.33
     manufacturers
    0.33
    POSITIVE LOGITS
    ुआ
    0.42
    旗
    0.41
    $<
    0.38
    )\|_{
    0.37
    }}}=
    0.37
    憲
    0.37
    プリント
    0.36
     असफल
    0.35
    叶
    0.34
     Haemat
    0.34
    Activations Density 0.000%

    No Known Activations