© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206341
    Prev
    Next
    INDEX
    Explanations

    say AI

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    艾
    0.65
     ай
    0.62
    Aid
    0.59
    アイ
    0.58
     איי
    0.57
    애
    0.56
    ай
    0.55
    Aye
    0.54
     Ayr
    0.53
    aye
    0.53
    POSITIVE LOGITS
     komplex
    0.40
    地说
    0.38
     коллеги
    0.35
     compleja
    0.35
    𒈬
    0.34
    Complex
    0.34
     frans
    0.34
     benefitting
    0.34
     लाभकारी
    0.33
     طریقہ
    0.33
    Activations Density 0.008%

    No Known Activations