© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52884
    Prev
    Next
    INDEX
    Explanations

    positive outcomes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    sorption
    0.40
    娑
    0.38
     Rous
    0.38
     elegantes
    0.38
     dwRes
    0.38
     separation
    0.37
    瑩
    0.37
    eleg
    0.36
    rarse
    0.36
     portability
    0.35
    POSITIVE LOGITS
     consomm
    0.41
     conclud
    0.41
     concl
    0.38
    ത്തിലേക്ക്
    0.37
     antit
    0.36
     impressing
    0.36
     کاب
    0.36
     Gareth
    0.35
    鬻
    0.35
     소비
    0.34
    Activations Density 0.003%

    No Known Activations