© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153421
    Prev
    Next
    INDEX
    Explanations

    release of gases, oil, memories

    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_23_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
    Pics
    0.35
    utan
    0.34
    oro
    0.32
     tranquil
    0.32
    udah
    0.32
    esta
    0.31
    letas
    0.31
    _'.$
    0.31
    Hot
    0.31
    etsu
    0.31
    POSITIVE LOGITS
     dữ
    0.36
     фай
    0.36
     Ka
    0.34
     음
    0.34
     ASSESSMENT
    0.34
    ষ
    0.34
    PROVIDER
    0.33
    普段
    0.33
    遺跡
    0.33
    PROVID
    0.33
    Activations Density 0.028%

    No Known Activations