© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248626
    Prev
    Next
    INDEX
    Explanations

    estimate tokens

    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
    setLayout
    0.39
    smoothing
    0.38
    l
    0.37
    Lay
    0.37
    press
    0.36
     Smoothing
    0.36
    overs
    0.35
    Side
    0.34
    necessary
    0.34
    Limit
    0.34
    POSITIVE LOGITS
     startups
    0.38
    ņu
    0.37
     silenz
    0.36
     skater
    0.35
    ഖ
    0.35
    ynchronously
    0.35
     personalised
    0.35
    isão
    0.34
     Trab
    0.34
     ▲
    0.34
    Activations Density 0.000%

    No Known Activations