© 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. 32486
    Prev
    Next
    INDEX
    Explanations

    original string/sentence/list/message

    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
     Access
    0.40
    いている
    0.37
    黨
    0.35
     Drop
    0.35
     Authorization
    0.35
    Access
    0.35
     designs
    0.34
     sá
    0.34
     Traverse
    0.34
    愀
    0.34
    POSITIVE LOGITS
    original
    0.46
    Original
    0.43
     Goodwin
    0.40
     Original
    0.39
     ORIGINAL
    0.38
    前期
    0.37
    GW
    0.37
     प्रीवियस
    0.37
    loginfo
    0.37
    ResponseType
    0.37
    Activations Density 0.007%

    No Known Activations