© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80211
    Prev
    Next
    INDEX
    Explanations

    startup: leadership, costs

    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_0_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
    a
    1.88
    ться
    1.51
    া
    1.45
    т
    1.44
    ت
    1.41
    จะ
    1.40
    ா
    1.38
    та
    1.31
    سی
    1.30
    ি
    1.28
    POSITIVE LOGITS
     for
    1.49
     at
    1.16
     to
    1.09
    ن
    1.08
     which
    1.02
     {})
    1.00
    ，
    1.00
    kannya
    0.97
    ión
    0.93
    此
    0.91
    Activations Density 0.001%

    No Known Activations