© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260930
    Prev
    Next
    INDEX
    Explanations

    sing along

    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
    ЕН
    0.40
    েন্সি
    0.39
    횽
    0.38
    reichen
    0.37
    CHARLES
    0.37
     kurs
    0.37
    エンド
    0.36
    EMAN
    0.36
     hydroxyl
    0.36
    ক্ট
    0.36
    POSITIVE LOGITS
     armoured
    0.47
     собстве
    0.46
    
    0.46
    ɫ
    0.44
     propria
    0.42
     asleep
    0.42
     vlastní
    0.41
     włas
    0.41
     personalisation
    0.41
    ŭ
    0.41
    Activations Density 0.001%

    No Known Activations