© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57078
    Prev
    Next
    INDEX
    Explanations

    from places

    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_11_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
     ética
    0.63
    ’
    0.58
    のは
    0.55
    少し
    0.55
    w
    0.55
    ρέ
    0.55
    нти
    0.54
    cer
    0.53
     aristocratic
    0.53
    bies
    0.51
    POSITIVE LOGITS
    樖
    0.53
     знаходиться
    0.50
     مواد
    0.50
    嘞
    0.50
    echolog
    0.49
    äude
    0.49
     ܕ
    0.49
     ד
    0.49
     তাপমাত্রা
    0.49
     कोणत्याही
    0.49
    Activations Density 0.001%

    No Known Activations