© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 118299
    Prev
    Next
    INDEX
    Explanations

    DC current and related electrical components

    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_38_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
     సై
    0.40
    (',');
    0.38
    紜
    0.38
    提
    0.38
    颧
    0.38
    letak
    0.38
    顴
    0.37
    噵
    0.37
     στρα
    0.36
    ቲክ
    0.35
    POSITIVE LOGITS
     DC
    0.41
    DC
    0.37
    raph
    0.36
     dc
    0.36
     blessings
    0.36
    蒲
    0.35
     underwent
    0.35
    yenne
    0.34
     dB
    0.33
     sapphire
    0.33
    Activations Density 0.001%

    No Known Activations