© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148955
    Prev
    Next
    INDEX
    Explanations

    function/code blocks

    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_23_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
    itek
    0.24
    larım
    0.24
    uck
    0.23
    thon
    0.23
    igraf
    0.23
    orek
    0.22
    uname
    0.22
    î
    0.22
     打开
    0.21
    isted
    0.21
    POSITIVE LOGITS
     інші
    0.22
    Connectivity
    0.21
    Problem
    0.21
     deficiency
    0.21
     fluctuation
    0.21
     bioavailability
    0.21
     ਵਿਚ
    0.21
     resignation
    0.21
     insufficiency
    0.21
     iyo
    0.20
    Activations Density 0.016%

    No Known Activations