© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134267
    Prev
    Next
    INDEX
    Explanations

    been + past/previous/any

    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_6_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
    es
    0.81
     for
    0.81
    ات
    0.81
    for
    0.76
    s
    0.75
    nd
    0.75
    8
    0.73
    I
    0.73
    iap
    0.72
     (
    0.70
    POSITIVE LOGITS
     an
    1.01
     alcuni
    0.91
    は
    0.87
    の
    0.87
    ro
    0.82
     pernah
    0.81
    :
    0.81
     sieci
    0.80
     largeur
    0.79
     czas
    0.79
    Activations Density 0.001%

    No Known Activations