© 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
    2. Gemma-3-27B-IT
    3. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 153976
    Prev
    Next
    INDEX
    Explanations

    constellation 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_23_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
     NHS
    0.41
    炁
    0.41
     CIS
    0.40
     Cylinder
    0.39
     هغه
    0.39
    ˣ
    0.38
    ʲ
    0.38
    了一种
    0.38
     aerobic
    0.37
     ROH
    0.37
    POSITIVE LOGITS
    Kevin
    0.43
    晦
    0.40
    オリ
    0.40
    kev
    0.40
     kev
    0.39
    onerror
    0.38
    sul
    0.38
    explique
    0.38
    Список
    0.37
    Goto
    0.37
    Activations Density 0.001%

    No Known Activations