© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246624
    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_40_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
     carriera
    0.43
    改正
    0.43
    ң
    0.41
     تلوار
    0.41
     නමුත්
    0.41
    quisition
    0.41
     rach
    0.40
    鼐
    0.39
    पालिका
    0.38
    钗
    0.38
    POSITIVE LOGITS
    anav
    0.35
    ítés
    0.35
    ','%
    0.33
    usega
    0.33
    vist
    0.32
     madam
    0.32
     interstit
    0.32
    Statements
    0.32
     Polska
    0.32
    ivum
    0.32
    Activations Density 0.000%

    No Known Activations