© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52577
    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
     Shouldn
    0.38
    地
    0.35
    改正
    0.35
    ITECT
    0.34
     cóm
    0.34
     ಪ್ರಮಾಣ
    0.34
     Pó
    0.34
    ḕ
    0.34
     lab
    0.34
     Cras
    0.34
    POSITIVE LOGITS
     joining
    0.55
     Joining
    0.43
    contrib
    0.42
    Joining
    0.42
    投入
    0.41
     joins
    0.40
     แนว
    0.38
     присоеди
    0.38
    เข้าร
    0.38
    Cold
    0.37
    Activations Density 0.000%

    No Known Activations