© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62137
    Prev
    Next
    INDEX
    Explanations

    trace or definition

    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
    im
    0.55
    on
    0.52
    s
    0.52
    сць
    0.51
    quark
    0.47
    it
    0.47
    way
    0.46
    warming
    0.46
    rekt
    0.46
    ain
    0.46
    POSITIVE LOGITS
    不足
    0.41
     ca
    0.40
     vetro
    0.40
     deficiency
    0.39
     documenti
    0.39
    τευ
    0.39
     آ
    0.37
     Venezuela
    0.37
     أبر
    0.37
     Bishops
    0.37
    Activations Density 0.030%

    No Known Activations