© 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
    2. Gemma-3-27B-IT
    3. 34-GEMMASCOPE-2-TRANSCODER-262K
    4. 18354
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    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_34_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
    一座
    0.40
     Meso
    0.37
    Esc
    0.37
     የእ
    0.37
     multid
    0.37
    ಇ
    0.36
    응
    0.36
    Ք
    0.36
     Послед
    0.36
     ВС
    0.35
    POSITIVE LOGITS
    녓
    0.34
    琕
    0.32
    finder
    0.32
     dominated
    0.31
    imals
    0.31
    alers
    0.31
    ທີ່
    0.31
    adora
    0.30
    bach
    0.30
    hani
    0.30
    Activations Density 0.010%

    No Known Activations