© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38370
    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_57_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
    यात
    0.44
    龚
    0.42
    墨西哥
    0.41
     ND
    0.40
    nay
    0.40
     Gina
    0.40
     romaine
    0.39
    Nay
    0.39
     Nay
    0.38
    ാനം
    0.38
    POSITIVE LOGITS
    asc
    0.40
    Mood
    0.37
    歲
    0.37
     Ar
    0.36
    Our
    0.36
    ဩ
    0.35
    歳
    0.35
     ऑ
    0.35
    ebilir
    0.35
     Asc
    0.35
    Activations Density 0.000%

    No Known Activations