© 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. 89915
    Prev
    Next
    INDEX
    Explanations

    defining characteristic

    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
    リム
    0.30
     signific
    0.28
     सिलेबस
    0.28
    ubishi
    0.28
    LJ
    0.28
    rufen
    0.28
     Significance
    0.27
    📝
    0.27
    wired
    0.27
     Signific
    0.27
    POSITIVE LOGITS
    फड
    0.32
     பகுதியில்
    0.29
    EndDate
    0.29
    поле
    0.29
    Regional
    0.27
    Chile
    0.27
    ContentLoaded
    0.27
     cracking
    0.27
    ഫോ
    0.27
    SearchResults
    0.27
    Activations Density 0.052%

    No Known Activations