© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18722
    Prev
    Next
    INDEX
    Explanations

    require, deny, grant, found, object

    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
     failing
    0.50
     fails
    0.49
     Fail
    0.47
     fail
    0.47
     Failing
    0.46
    Fail
    0.44
     Losing
    0.44
    싣
    0.40
     losing
    0.40
     gagal
    0.39
    POSITIVE LOGITS
     bals
    0.43
    abe
    0.42
     mand
    0.41
    ABE
    0.40
    Skippable
    0.40
    ukt
    0.36
     sals
    0.34
    squa
    0.34
     sape
    0.34
    sal
    0.33
    Activations Density 0.022%

    No Known Activations