© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38500
    Prev
    Next
    INDEX
    Explanations

    Dialogflow CX

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    あまり
    0.68
    ५
    0.66
    क
    0.59
    すでに
    0.58
    幷
    0.58
     đưa
    0.57
    ここ
    0.57
    TED
    0.56
    k
    0.56
     désormais
    0.56
    POSITIVE LOGITS
    0
    0.73
     Isn
    0.64
    ْب
    0.64
     участке
    0.62
    isomer
    0.59
    0.59
    ı
    0.56
    INFO
    0.56
    ین
    0.54
     asesin
    0.54
    Activations Density 0.001%

    No Known Activations