© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91450
    Prev
    Next
    INDEX
    Explanations

    Anderson names

    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_11_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
    н
    0.64
    n
    0.52
    ks
    0.51
    keit
    0.51
    aw
    0.51
    ף
    0.51
    lay
    0.49
    枓
    0.49
    м
    0.48
    kel
    0.48
    POSITIVE LOGITS
    गमन
    0.58
     médical
    0.54
    服务的
    0.53
     ćete
    0.51
     Sonora
    0.50
    áva
    0.50
     vintage
    0.50
     σας
    0.49
     νέ
    0.49
    駛
    0.49
    Activations Density 0.000%

    No Known Activations