© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236320
    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_46_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
    へ
    0.36
    secutive
    0.34
    ழை
    0.33
     Reactive
    0.33
    ileged
    0.33
    ക്കെ
    0.33
     DIM
    0.32
    ジー
    0.32
     Containers
    0.32
     دق
    0.32
    POSITIVE LOGITS
    每一个
    0.45
    ือด
    0.42
     প্রতিটি
    0.42
    潾
    0.40
     ag
    0.40
    метри
    0.39
     acacia
    0.39
    Ag
    0.39
    Benefit
    0.38
     hyd
    0.38
    Activations Density 0.000%

    No Known Activations