© 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. 218560
    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
     itens
    0.41
     पैटर्न
    0.38
    Sexo
    0.36
    Zeros
    0.36
     items
    0.35
     multipl
    0.35
    ">%
    0.35
    有人
    0.34
    ابان
    0.34
     있으면
    0.34
    POSITIVE LOGITS
     Memorandum
    0.38
    શ્
    0.38
    蝼
    0.38
     Possession
    0.37
    誅
    0.37
     Germ
    0.36
     Memor
    0.36
    လုံး
    0.36
    成本
    0.35
     Removal
    0.35
    Activations Density 0.000%

    No Known Activations