© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86372
    Prev
    Next
    INDEX
    Explanations

    shadow on the moon

    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_18_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
    T
    0.56
    ">
    0.55
    /
    0.53
    W
    0.53
    ー
    0.53
    O
    0.49
    Agent
    0.48
    Cam
    0.48
    のような
    0.48
    알
    0.48
    POSITIVE LOGITS
     فَ
    0.49
    érrez
    0.49
    ará
    0.48
     ساده
    0.47
     énfasis
    0.47
    ত্যার
    0.45
    jectories
    0.45
     possibili
    0.45
    erdapat
    0.44
    嫖
    0.44
    Activations Density 0.000%

    No Known Activations