© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199193
    Prev
    Next
    INDEX
    Explanations

    deserts and cheese

    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_46_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
    मिका
    0.42
    款
    0.41
    FBSDKSettings
    0.41
     Nie
    0.40
     gestational
    0.39
    溌
    0.39
    ័យ
    0.39
    %%%%%%%%
    0.38
    Luck
    0.38
    Ups
    0.37
    POSITIVE LOGITS
    rtList
    0.39
    lyde
    0.39
     মুখে
    0.38
     পিছনে
    0.38
     accumulated
    0.37
    バレ
    0.37
    र्च
    0.37
     klo
    0.36
     Mauer
    0.36
    积累
    0.36
    Activations Density 0.008%

    No Known Activations