© 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. 241982
    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
    フェア
    0.39
    믿
    0.37
    bitkan
    0.36
    ⿹
    0.36
    offic
    0.36
     weak
    0.35
    Fair
    0.35
    tiket
    0.35
     செய்
    0.34
    Таким
    0.34
    POSITIVE LOGITS
    say
    0.45
    Say
    0.43
     Say
    0.41
    說
    0.41
     کوشش
    0.41
    經
    0.39
    urel
    0.39
     holly
    0.38
     आंकड़ों
    0.38
    ipel
    0.38
    Activations Density 0.000%

    No Known Activations