© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163933
    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_31_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
    殓
    0.34
    agawa
    0.34
    ティーク
    0.34
    ʄ
    0.34
    sports
    0.33
    Wanted
    0.33
    燐
    0.33
     Unusual
    0.32
     Uncomment
    0.32
     よく
    0.32
    POSITIVE LOGITS
     rol
    0.38
    더
    0.38
     achet
    0.37
     leps
    0.37
    უქ
    0.37
     Juel
    0.36
    জার
    0.36
     mollis
    0.36
     BBS
    0.36
     बद
    0.35
    Activations Density 0.000%

    No Known Activations