© 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. 85142
    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
    らない
    0.43
    sail
    0.41
    ALS
    0.41
    Maine
    0.40
    에서
    0.40
    하지
    0.39
    situ
    0.39
    와
    0.39
    Vermont
    0.38
    Oper
    0.38
    POSITIVE LOGITS
     nanoscale
    0.43
     toutefois
    0.41
     audience
    0.40
     insidious
    0.40
     émotion
    0.40
    ắng
    0.39
     लीजिएगा
    0.39
     learnt
    0.38
     reinforcements
    0.38
     असल्याचे
    0.38
    Activations Density 0.000%

    No Known Activations