© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153678
    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_23_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
     acquis
    0.46
     SWITCH
    0.43
    équip
    0.42
    ലൈ
    0.41
     professional
    0.41
     fiancé
    0.41
    ༡
    0.41
    ಸ್ಕೊ
    0.40
     televis
    0.40
     phytochemical
    0.40
    POSITIVE LOGITS
    ంట
    0.46
    wid
    0.44
    antd
    0.44
     vẫn
    0.43
     परवानगी
    0.43
    垫
    0.43
    वरून
    0.43
     जाणून
    0.42
    िंग
    0.42
    wave
    0.42
    Activations Density 0.000%

    No Known Activations