© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202848
    Prev
    Next
    INDEX
    Explanations

    say "hover"

    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_46_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
    脣
    0.41
    รั่ง
    0.40
    nonpayable
    0.39
    賏
    0.38
    枟
    0.38
    ake
    0.37
     తొ
    0.36
    atchewan
    0.36
    elti
    0.36
     khand
    0.35
    POSITIVE LOGITS
     touch
    0.85
     touching
    0.83
     touched
    0.82
    触
    0.74
     touches
    0.73
     Touch
    0.71
    touch
    0.70
    Touch
    0.70
     toucher
    0.69
    TOUCH
    0.68
    Activations Density 0.002%

    No Known Activations