© 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. 8969
    Prev
    Next
    INDEX
    Explanations

    California Consumer Privacy Act

    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
     Shanks
    0.37
    OUBLE
    0.36
     NO
    0.35
     lark
    0.35
    額
    0.35
     dou
    0.35
    Rez
    0.35
     changé
    0.35
    ಘ
    0.35
     TE
    0.35
    POSITIVE LOGITS
     California
    0.51
    California
    0.50
     Californian
    0.46
    Calif
    0.45
     california
    0.45
     Calif
    0.44
     Кали
    0.40
     Californians
    0.39
     Californ
    0.39
     Kaliforn
    0.38
    Activations Density 0.001%

    No Known Activations