© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148492
    Prev
    Next
    INDEX
    Explanations

    weight lifting

    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_59_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
    an
    0.93
    aní
    0.63
    ان
    0.59
    o
    0.51
    anlı
    0.50
    aný
    0.50
    aniline
    0.47
    𒀀
    0.42
    antera
    0.42
    anic
    0.42
    POSITIVE LOGITS
     residuals
    0.40
    दीश
    0.40
    end
    0.39
    n
    0.39
     mt
    0.39
     foc
    0.37
    நோய
    0.37
     clout
    0.37
     nvp
    0.37
     disease
    0.37
    Activations Density 0.001%

    No Known Activations