© 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. 200294
    Prev
    Next
    INDEX
    Explanations

    Mississippi

    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
     fats
    0.45
    醐
    0.40
     Fats
    0.40
     brewery
    0.39
    䡇
    0.39
    FAs
    0.39
    मो
    0.38
    脂肪
    0.37
     kabupaten
    0.37
    mtext
    0.37
    POSITIVE LOGITS
     V
    0.53
     VGA
    0.47
     Vick
    0.42
     Lynx
    0.42
     cycl
    0.40
     Irma
    0.40
     linearization
    0.39
    énieur
    0.39
     возра
    0.38
     Lin
    0.38
    Activations Density 0.000%

    No Known Activations