© 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. 262019
    Prev
    Next
    INDEX
    Explanations

    gently stir or fold

    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
    Ṣ
    0.46
     selepas
    0.45
     Glad
    0.43
     teško
    0.43
     erős
    0.42
    哔
    0.41
     બ
    0.41
    لیسی
    0.41
     Safety
    0.40
     caméra
    0.40
    POSITIVE LOGITS
    "));
    0.41
    靠
    0.41
     CAN
    0.40
    currently
    0.40
    有所
    0.40
     фундамента
    0.39
    最高の
    0.38
     guidelines
    0.38
     Currently
    0.37
     dile
    0.37
    Activations Density 0.003%

    No Known Activations