© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117169
    Prev
    Next
    INDEX
    Explanations

    differs from

    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_27_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
    上前
    0.44
    (_,
    0.42
    нодоро
    0.37
    唳
    0.35
    nPortIndex
    0.35
    ሑ
    0.35
    newParameter
    0.34
     صدي
    0.34
     phụ
    0.33
    (_)
    0.33
    POSITIVE LOGITS
     niacin
    0.44
     copious
    0.41
     CentOS
    0.40
    Plan
    0.40
     hibernation
    0.39
     yogurt
    0.39
     cocoa
    0.39
    ંબા
    0.38
     원래
    0.38
     plan
    0.38
    Activations Density 0.004%

    No Known Activations