© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102842
    Prev
    Next
    INDEX
    Explanations

    under/over bets

    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_16_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
    د
    0.53
    ד
    0.51
    ک
    0.48
    लाम
    0.47
     WERE
    0.46
    ی
    0.46
     direitos
    0.45
    ങ്ങള
    0.45
     Hiện
    0.45
    س
    0.45
    POSITIVE LOGITS
    恴
    0.52
     aversion
    0.44
    áis
    0.44
    qli
    0.43
    вым
    0.43
    isu
    0.42
     masala
    0.42
    γκε
    0.42
     mindfulness
    0.41
     inboard
    0.41
    Activations Density 0.000%

    No Known Activations