© 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. 77847
    Prev
    Next
    INDEX
    Explanations

    here

    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
     nam
    0.46
    nam
    0.41
    Nam
    0.40
    лам
    0.39
     Following
    0.38
    .'%
    0.37
    ஃ
    0.37
    ｆ
    0.37
    ழ
    0.36
    פול
    0.36
    POSITIVE LOGITS
     úrov
    0.48
     budd
    0.47
     whim
    0.46
     уровня
    0.46
     Budd
    0.45
     whims
    0.44
     уров
    0.43
     levels
    0.43
     Lax
    0.42
     ระบบ
    0.42
    Activations Density 0.017%

    No Known Activations