© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45069
    Prev
    Next
    INDEX
    Explanations

    one of

    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_13_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
     encuentran
    0.64
    σαν
    0.61
    艨
    0.61
     trovano
    0.59
     permangan
    0.58
     vrch
    0.57
    మంది
    0.55
     victoire
    0.55
     verzi
    0.54
    રોના
    0.54
    POSITIVE LOGITS
    a
    0.88
    f
    0.84
    one
    0.80
    o
    0.70
    F
    0.68
     one
    0.65
    me
    0.64
     an
    0.63
    if
    0.62
    AP
    0.61
    Activations Density 0.000%

    No Known Activations