© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45416
    Prev
    Next
    INDEX
    Explanations

    timeline creation or exploration

    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_22_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
    ının
    0.48
    台灣
    0.47
    षेक
    0.42
    itation
    0.41
    导
    0.41
    台湾
    0.40
     sic
    0.40
    语音
    0.40
     Ting
    0.39
     SAMSUNG
    0.39
    POSITIVE LOGITS
    produtos
    0.48
     conceitos
    0.47
    Hình
    0.43
    ቕ
    0.41
    CHREIBUNG
    0.41
    usional
    0.40
     naturais
    0.40
    ベクトル
    0.40
    гур
    0.39
     элемент
    0.39
    Activations Density 0.000%

    No Known Activations