© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 102147
    Prev
    Next
    INDEX
    Explanations

    technical computing

    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_44_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
     মাথা
    0.41
     útil
    0.40
    %!
    0.39
    드릴
    0.39
    assertRaises
    0.38
     defaultConfig
    0.37
     problemática
    0.37
     conglomerates
    0.36
    Parsed
    0.35
    娆
    0.35
    POSITIVE LOGITS
     Sainsbury
    0.42
     Wallis
    0.42
    eff
    0.41
    錫
    0.40
     invisible
    0.39
     Indus
    0.38
     workshop
    0.38
    舌
    0.38
     जो
    0.38
    invisible
    0.38
    Activations Density 0.013%

    No Known Activations