© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 164655
    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
    ＰＥＮＡＮＡ
    0.42
     అభి
    0.40
    ారో
    0.39
    hotite
    0.39
    담당
    0.37
    푞
    0.37
     Brun
    0.37
     domicili
    0.37
    Cadastro
    0.36
     PKR
    0.36
    POSITIVE LOGITS
     comforts
    0.36
    を楽しむ
    0.36
    喜
    0.35
    聚合
    0.35
    Joy
    0.34
    raya
    0.34
    dda
    0.33
    これも
    0.33
    sson
    0.33
    楽しみ
    0.33
    Activations Density 0.000%

    No Known Activations