© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213906
    Prev
    Next
    INDEX
    Explanations

    decl

    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_50_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
     zwei
    0.38
    ?')
    0.38
     zwölf
    0.38
    ?]
    0.37
     ஏழு
    0.37
    .'.
    0.36
    ಬ್ಬ
    0.35
    列
    0.35
    >`
    0.35
    zil
    0.35
    POSITIVE LOGITS
     decl
    0.54
    decl
    0.50
     declining
    0.49
     Decl
    0.47
     fors
    0.47
    Decl
    0.45
     declined
    0.45
     declines
    0.45
     FF
    0.44
     yas
    0.43
    Activations Density 0.002%

    No Known Activations