© 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. 250702
    Prev
    Next
    INDEX
    Explanations

    say taste

    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
     t
    0.57
     tasting
    0.55
     rock
    0.48
     l
    0.45
     ت
    0.45
     inhale
    0.44
    サービス
    0.44
     crumble
    0.43
     Tasting
    0.43
     st
    0.43
    POSITIVE LOGITS
     name
    0.46
     მხ
    0.40
    aggregated
    0.39
     bites
    0.38
     Eats
    0.38
    历
    0.38
    নাম
    0.37
     Bites
    0.37
    alık
    0.36
    smoke
    0.36
    Activations Density 0.002%

    No Known Activations