© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 117514
    Prev
    Next
    INDEX
    Explanations

    title definition in code

    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_38_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
    screen
    0.39
    Screen
    0.36
     Screen
    0.35
    rap
    0.35
     screen
    0.35
    дык
    0.34
    Elev
    0.34
    н
    0.34
     screens
    0.34
    Transfer
    0.34
    POSITIVE LOGITS
     intervened
    0.41
     strcat
    0.40
     talisman
    0.40
     exit
    0.39
     ৪০০
    0.39
    branchNode
    0.39
     exited
    0.39
     യൂ
    0.39
    缡
    0.39
    :`
    0.38
    Activations Density 0.000%

    No Known Activations