© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52507
    Prev
    Next
    INDEX
    Explanations

    time, node, sup, total, local, author, day, zero, google

    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_31_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
    irdik
    0.38
    solvent
    0.37
     வெறு
    0.35
     நீண்ட
    0.33
     lokale
    0.33
    𝚝
    0.33
    Local
    0.33
    本地
    0.33
    商务
    0.33
    hardware
    0.32
    POSITIVE LOGITS
     applying
    0.38
     kože
    0.38
    ⿲
    0.36
    ँचा
    0.36
     ਘ
    0.36
     chord
    0.35
    ταν
    0.35
     sintomas
    0.35
     spins
    0.34
     ပါ
    0.34
    Activations Density 0.000%

    No Known Activations