© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20431
    Prev
    Next
    INDEX
    Explanations

    academic and German text

    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_56_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
     ढु
    0.39
     Zug
    0.39
     G
    0.38
    lery
    0.38
     নামক
    0.38
     varieg
    0.37
    cimento
    0.37
     votes
    0.36
    Zug
    0.35
    Olive
    0.35
    POSITIVE LOGITS
     dazu
    0.54
    ിക്കുകയും
    0.37
    瞎
    0.37
    subsetneq
    0.35
    ardless
    0.35
     silk
    0.34
    esian
    0.34
    भीत
    0.34
    Silk
    0.34
    ίζ
    0.34
    Activations Density 0.008%

    No Known Activations