© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252353
    Prev
    Next
    INDEX
    Explanations

    methane

    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
     M
    2.34
     М
    1.71
    m
    1.71
     ম
    1.64
     m
    1.63
     म
    1.62
     الم
    1.59
    M
    1.52
     м
    1.43
    <0xA0>
    1.39
    POSITIVE LOGITS
     mating
    0.54
    ቃ
    0.36
     mated
    0.35
    ंड
    0.34
    ANDEZ
    0.32
    minipage
    0.32
    鵑
    0.31
     विभा
    0.31
    Mens
    0.31
    ITECT
    0.31
    Activations Density 0.005%

    No Known Activations