© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175096
    Prev
    Next
    INDEX
    Explanations

    current time or state

    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_20_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
    );
    0.53
     Auge
    0.43
     సందర్భ
    0.41
     سجل
    0.41
    ্লিকেশন
    0.40
     También
    0.39
    ブック
    0.39
    explos
    0.39
    Merc
    0.38
    ),
    0.38
    POSITIVE LOGITS
     shortage
    0.43
    ❧
    0.42
     Airports
    0.41
    ंजी
    0.41
     DURING
    0.41
     BEFORE
    0.40
    ারিত
    0.39
    ផលិត
    0.39
    灵
    0.39
     DHA
    0.38
    Activations Density 0.000%

    No Known Activations