© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41550
    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_22_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
    炒
    0.47
     bashing
    0.45
     conjectures
    0.44
     illusions
    0.44
     foray
    0.43
     manipulations
    0.42
     mathrm
    0.42
    鉭
    0.41
     alg
    0.40
     moderation
    0.40
    POSITIVE LOGITS
    ì
    0.50
    icularis
    0.50
    "=>
    0.49
     می‌دهد
    0.49
    adisu
    0.47
    anjutkan
    0.47
    ">[
    0.47
    instrList
    0.46
     cidade
    0.45
     Ли
    0.45
    Activations Density 0.000%

    No Known Activations