© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116745
    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_27_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
     Incoming
    0.39
     মনে
    0.37
     osobow
    0.36
    ::__
    0.36
     panne
    0.34
    Incoming
    0.34
    ↵↵↵↵
    0.33
     Tw
    0.33
     നിര
    0.33
    倒
    0.33
    POSITIVE LOGITS
    WriteString
    0.40
     الإنسان
    0.39
    Ḍ
    0.39
    Compression
    0.38
    சியா
    0.37
    <unused23>
    0.36
     सहयोग
    0.36
    兼容
    0.36
    我們的
    0.36
    চার্জ
    0.35
    Activations Density 0.000%

    No Known Activations