© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41854
    Prev
    Next
    INDEX
    Explanations

    deep learning, blockchain, automation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
     và
    0.43
    iciência
    0.40
    와
    0.39
     و
    0.38
     ו
    0.38
     અને
    0.37
    과
    0.37
    以下
    0.36
     Immortal
    0.34
    습니다
    0.34
    POSITIVE LOGITS
     ڈھاکہ
    0.38
     folly
    0.37
     хам
    0.35
    郢
    0.34
    ]=\
    0.34
     heterogeneity
    0.33
     मेर
    0.33
     गोवा
    0.33
    蟲
    0.32
     Харків
    0.32
    Activations Density 0.028%

    No Known Activations