© 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. 3028
    Prev
    Next
    INDEX
    Explanations

    power or linear electronics

    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
    茅
    0.39
     FUT
    0.38
     ame
    0.38
    setRoot
    0.37
    श्न
    0.37
     hCG
    0.37
    ահ
    0.37
     warranted
    0.36
    懋
    0.36
     schizophren
    0.36
    POSITIVE LOGITS
     Power
    0.54
     power
    0.51
    linear
    0.50
    Power
    0.50
    power
    0.47
    rf
    0.47
     linear
    0.44
     POWER
    0.41
     lineal
    0.40
    线性
    0.39
    Activations Density 0.060%

    No Known Activations