© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204799
    Prev
    Next
    INDEX
    Explanations

    key sections

    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_25_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
     증
    0.41
     삶
    0.36
     Relevance
    0.36
     subsum
    0.35
    證
    0.34
    证
    0.34
     яс
    0.33
    evident
    0.33
    룩
    0.33
     돌
    0.33
    POSITIVE LOGITS
     insbesondere
    0.45
    )));
    0.43
     Mü
    0.43
     jeho
    0.42
     tenga
    0.42
     Tät
    0.42
    ốc
    0.41
     jego
    0.40
     avrà
    0.40
     его
    0.40
    Activations Density 0.000%

    No Known Activations