© 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. 52336
    Prev
    Next
    INDEX
    Explanations

    0

    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
     ten
    0.70
    十
    0.70
     ۱۰
    0.65
     १०
    0.60
     ১০
    0.59
     Ten
    0.58
     десяти
    0.57
     दस
    0.56
    १०
    0.55
     zehn
    0.55
    POSITIVE LOGITS
     Inverse
    0.39
    ^{-
    0.38
    Ordered
    0.38
    E
    0.38
    inverse
    0.38
    uldig
    0.38
    ourced
    0.37
     inverse
    0.37
     inversa
    0.35
    Inverse
    0.35
    Activations Density 0.003%

    No Known Activations