© 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. 153235
    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
    bel
    0.24
     Silas
    0.24
     wegen
    0.24
    lementine
    0.23
    蜜
    0.23
     due
    0.22
     non
    0.22
     penalty
    0.22
    .#
    0.22
    climate
    0.22
    POSITIVE LOGITS
    クロマト
    0.29
     ক্রমা
    0.27
    pInBuffer
    0.26
    嬗
    0.26
     görül
    0.26
     xbox
    0.26
     pTM
    0.25
    номет
    0.25
    前記
    0.25
     abhid
    0.25
    Activations Density 0.000%

    No Known Activations