© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31832
    Prev
    Next
    INDEX
    Explanations

    shogun

    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_50_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
    ক
    0.52
     Pipelines
    0.48
    Pierre
    0.45
    PIPE
    0.45
    ARA
    0.45
     pier
    0.44
    PACK
    0.44
     piers
    0.43
     Planck
    0.42
     галакти
    0.41
    POSITIVE LOGITS
     ш
    0.50
    shid
    0.46
     sh
    0.45
    muk
    0.45
    mu
    0.45
    Sh
    0.43
     shogun
    0.43
    ior
    0.42
     Muk
    0.42
     mu
    0.41
    Activations Density 0.008%

    No Known Activations