© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62351
    Prev
    Next
    INDEX
    Explanations

    say "y"

    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
     condición
    0.39
     які
    0.39
    ('&
    0.39
     बारे
    0.37
     (&
    0.37
     incluyendo
    0.37
     включая
    0.36
     chrysanthemum
    0.36
     zeal
    0.36
     ملک
    0.36
    POSITIVE LOGITS
     and
    0.59
     an
    0.55
    and
    0.52
     y
    0.52
    solo
    0.44
     solo
    0.42
    Solo
    0.41
     mi
    0.41
     Y
    0.41
    alone
    0.40
    Activations Density 0.005%

    No Known Activations