© 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. 7433
    Prev
    Next
    INDEX
    Explanations

    algorithm analysis, data structures, self-balancing trees

    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
     Chowdh
    0.38
     persecution
    0.36
     entreprene
    0.35
     Chaudhary
    0.35
     proc
    0.35
     _______
    0.34
     réflex
    0.34
    ᚄ
    0.34
    oggles
    0.34
    thati
    0.34
    POSITIVE LOGITS
     randomized
    0.48
     amort
    0.42
    HAEL
    0.40
     randomization
    0.40
    zież
    0.39
    Mit
    0.38
    amort
    0.38
     अम
    0.38
    もなく
    0.37
     Moving
    0.36
    Activations Density 0.048%

    No Known Activations