© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 182684
    Prev
    Next
    INDEX
    Explanations

    SQL schema descriptions

    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_29_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
    Ｉ
    0.38
    ভৃতি
    0.37
     பாதிக்கப்பட்ட
    0.36
    lic
    0.35
    様々な
    0.35
     WIL
    0.34
    Various
    0.34
    法
    0.33
    Grid
    0.32
     Supports
    0.32
    POSITIVE LOGITS
     negras
    0.43
     biennium
    0.42
     pistachio
    0.41
     great
    0.40
     bunny
    0.39
     noires
    0.39
     galerie
    0.39
    oradi
    0.38
     nitro
    0.38
     obt
    0.38
    Activations Density 0.000%

    No Known Activations