© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46438
    Prev
    Next
    INDEX
    Explanations

    True North, True Love

    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_3_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
    ።
    0.70
     biển
    0.66
     conjectured
    0.63
     hơn
    0.61
    複数の
    0.59
     jeruk
    0.59
     bialgebras
    0.59
    ÑA
    0.59
    äänt
    0.59
     Labrenzia
    0.58
    POSITIVE LOGITS
    t
    1.04
    p
    0.88
    u
    0.84
     (
    0.81
    ل
    0.81
    l
    0.78
    на
    0.77
    v
    0.76
    c
    0.73
    ud
    0.70
    Activations Density 0.001%

    No Known Activations