© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243812
    Prev
    Next
    INDEX
    Explanations

    npm install, run, start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    燉
    0.42
    தமாக
    0.40
     tutorials
    0.39
     priori
    0.38
    Numerical
    0.38
     ತ
    0.37
     Provided
    0.36
    맘
    0.36
     instructional
    0.36
    𝙡
    0.36
    POSITIVE LOGITS
    емым
    0.41
     पढ़े
    0.39
    यत
    0.39
     Gateway
    0.38
    ন্দ
    0.38
     descending
    0.38
     seekBar
    0.37
     Gage
    0.37
    করণ
    0.37
    ണേ
    0.37
    Activations Density 0.001%

    No Known Activations