© 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. 7673
    Prev
    Next
    INDEX
    Explanations

    busy mom

    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
    िकुलम
    0.38
    insa
    0.35
    𐰴
    0.34
     raised
    0.34
    CreateInfo
    0.34
    ikut
    0.34
    ρούν
    0.34
    FORMATION
    0.33
    Raised
    0.33
    filesystem
    0.33
    POSITIVE LOGITS
     father
    2.36
     mother
    2.25
     fathers
    1.98
    father
    1.97
     mothers
    1.91
    mother
    1.89
     père
    1.83
    父
    1.81
     mãe
    1.80
     бать
    1.77
    Activations Density 0.045%

    No Known Activations