© 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. 18206
    Prev
    Next
    INDEX
    Explanations

    nn.Module

    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
     arg
    0.56
    Arg
    0.45
     didReceive
    0.42
     arguing
    0.42
    didReceive
    0.42
     Arg
    0.42
    嘩
    0.41
    Afrika
    0.40
     argumentative
    0.39
    Dictionary
    0.38
    POSITIVE LOGITS
     Institution
    0.46
    avelength
    0.40
    藓
    0.40
     nn
    0.39
     автоном
    0.39
     अखंड
    0.39
     편리
    0.39
    自治区
    0.38
    کرات
    0.38
     آزاد
    0.37
    Activations Density 0.006%

    No Known Activations