© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142472
    Prev
    Next
    INDEX
    Explanations

    name

    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_46_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
    klich
    0.42
    šnj
    0.38
     テーマ
    0.38
     ビ
    0.37
    qx
    0.37
     skiprows
    0.37
    rikes
    0.37
     Wrapping
    0.36
     ప్రజా
    0.35
    翎
    0.35
    POSITIVE LOGITS
     English
    0.44
     officer
    0.43
     англий
    0.43
     IPA
    0.41
     अंग्रेजी
    0.41
     Erde
    0.41
     Autof
    0.40
     Oliva
    0.40
     Oliver
    0.39
     തുടങ്ങ
    0.39
    Activations Density 0.005%

    No Known Activations