© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41889
    Prev
    Next
    INDEX
    Explanations

    variable declaration `x`

    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_22_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
    {
    0.42
    Admin
    0.40
    Network
    0.39
    examine
    0.38
    Web
    0.37
    Execute
    0.37
    Ω
    0.37
     Examine
    0.36
    чнее
    0.36
    श
    0.36
    POSITIVE LOGITS
     divor
    0.46
    anche
    0.45
    ാർ
    0.44
     conqu
    0.44
     инвести
    0.44
     desigual
    0.43
     Frau
    0.43
     Eti
    0.43
     నాగ
    0.42
     कारों
    0.42
    Activations Density 0.000%

    No Known Activations