© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156688
    Prev
    Next
    INDEX
    Explanations

    mountains and roads

    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
     hy
    0.45
    zcan
    0.43
     ર
    0.40
     ক্লে
    0.40
    क्ले
    0.39
     Kaly
    0.38
     G
    0.38
     Claus
    0.38
     kle
    0.37
     जीडी
    0.37
    POSITIVE LOGITS
    柰
    0.40
    钛
    0.40
    ковых
    0.39
     MHC
    0.39
    oluene
    0.38
    ຫມ
    0.38
    ussa
    0.38
     MH
    0.37
     x
    0.37
     बेह
    0.37
    Activations Density 0.000%

    No Known Activations