© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252201
    Prev
    Next
    INDEX
    Explanations

    code or structured text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     mago
    0.34
     SOLID
    0.33
     syd
    0.33
     bright
    0.32
     specialised
    0.32
    𝐡
    0.32
     süd
    0.31
     `"
    0.31
     mə
    0.31
     skimming
    0.31
    POSITIVE LOGITS
     conced
    0.36
    As
    0.32
    izace
    0.30
    dozen
    0.30
    Computing
    0.29
     spis
    0.29
    JP
    0.29
     decenas
    0.29
    Path
    0.28
    Wayne
    0.28
    Activations Density 0.011%

    No Known Activations