© 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. 217962
    Prev
    Next
    INDEX
    Explanations

    testing code

    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
    рованная
    0.44
    差別
    0.43
    闕
    0.43
    鉞
    0.41
    Plate
    0.40
    偶然
    0.40
    objClass
    0.40
    -)
    0.39
    Вот
    0.38
    mog
    0.38
    POSITIVE LOGITS
    agree
    0.41
     والص
    0.39
    grit
    0.38
     grit
    0.37
    ns
    0.35
     Mastercard
    0.35
    IRST
    0.35
     Grit
    0.34
     inh
    0.34
    گیر
    0.34
    Activations Density 0.000%

    No Known Activations