© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77346
    Prev
    Next
    INDEX
    Explanations

    natural gaps

    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_53_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
     pe
    0.44
     PE
    0.44
    PE
    0.43
    페
    0.40
     क
    0.38
     বিত
    0.37
     callers
    0.37
    يلات
    0.37
     ranked
    0.36
    が通販
    0.36
    POSITIVE LOGITS
    числи
    0.43
    dc
    0.43
    cannon
    0.40
    apped
    0.40
     натура
    0.39
    ieson
    0.38
    荸
    0.38
    natural
    0.38
    एनएस
    0.38
    APPED
    0.38
    Activations Density 0.014%

    No Known Activations