© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61290
    Prev
    Next
    INDEX
    Explanations

    say "k" words

    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
     assumes
    0.40
     triang
    0.39
     lemmas
    0.39
    αν
    0.38
     dahin
    0.38
    (*(
    0.37
     Coleman
    0.37
     dictates
    0.37
    webElementXpaths
    0.37
    ί
    0.37
    POSITIVE LOGITS
    k
    0.62
    kult
    0.48
    kry
    0.47
    eneo
    0.46
    kond
    0.46
    kup
    0.45
    ing
    0.43
    kob
    0.42
    Stand
    0.41
    ೃ
    0.41
    Activations Density 0.000%

    No Known Activations