© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166542
    Prev
    Next
    INDEX
    Explanations

    acknowledging sadness, normal human emotion

    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
    លេ
    0.44
    ɪ
    0.37
     ली
    0.37
    logged
    0.36
    outlined
    0.36
    gras
    0.35
    TRO
    0.35
    <_
    0.34
     επ
    0.34
     entsprechende
    0.34
    POSITIVE LOGITS
     occasionally
    0.53
    偶尔
    0.50
     occasional
    0.49
     Occasionally
    0.46
     недель
    0.40
    Occasionally
    0.40
     Bootstrap
    0.39
     premat
    0.39
     cardiomyocytes
    0.38
     siRNA
    0.37
    Activations Density 0.010%

    No Known Activations