© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45743
    Prev
    Next
    INDEX
    Explanations

    why should I

    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_13_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
     Jiménez
    0.42
    ὰ
    0.40
    している
    0.39
    ières
    0.37
    </td>
    0.36
     ενώ
    0.36
     výbě
    0.36
     Withers
    0.36
     EN
    0.36
     F
    0.35
    POSITIVE LOGITS
     do
    0.46
    tfine
    0.45
    𝗻
    0.42
     تھے
    0.41
    ຊີ
    0.39
     그렇
    0.39
     הח
    0.38
    𝗸
    0.38
    nare
    0.38
    PIRE
    0.38
    Activations Density 0.013%

    No Known Activations