© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 217995
    Prev
    Next
    INDEX
    Explanations

    Acne Acer

    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_47_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
    পল
    0.37
    лица
    0.36
    поли
    0.36
    桐
    0.36
    ッツ
    0.35
    หนด
    0.35
     NSError
    0.35
     спеціа
    0.35
     мир
    0.34
    Ꭱ
    0.34
    POSITIVE LOGITS
     Darm
    0.43
     Cole
    0.43
    ramento
    0.41
     iniciado
    0.39
    chiha
    0.39
     Brito
    0.38
    cole
    0.38
    वय
    0.38
    izon
    0.38
    ismo
    0.38
    Activations Density 0.000%

    No Known Activations