© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15469
    Prev
    Next
    INDEX
    Explanations

    cannot provide medical advice

    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_40_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
    Retrie
    0.43
    Mais
    0.41
     निर्देशन
    0.40
    语文
    0.40
    recomend
    0.40
    뺨
    0.39
     نصی
    0.39
    就能
    0.39
    掫
    0.39
     botan
    0.37
    POSITIVE LOGITS
     passing
    0.57
     pass
    0.50
    passing
    0.46
     passes
    0.44
     Passing
    0.44
    pass
    0.43
     sund
    0.43
     passer
    0.42
    Passing
    0.42
     Pass
    0.42
    Activations Density 0.004%

    No Known Activations