© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246243
    Prev
    Next
    INDEX
    Explanations

    initialization with zeros

    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_40_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
    黑色
    0.45
     iza
    0.43
     黑
    0.41
     BLACK
    0.38
     tesam
    0.36
     THOM
    0.35
    BLACK
    0.35
     vutto
    0.35
     черный
    0.35
     زيت
    0.35
    POSITIVE LOGITS
    Avg
    0.41
    Já
    0.39
    ε
    0.39
     Já
    0.38
    koch
    0.38
    ન્ડ
    0.38
    bahn
    0.37
    horns
    0.37
     டிவி
    0.37
    Caprio
    0.37
    Activations Density 0.001%

    No Known Activations