© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46249
    Prev
    Next
    INDEX
    Explanations

    under legal provisions and sections

    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
    ३
    0.67
     όλ
    0.64
    𝟰
    0.62
    राणिक
    0.61
     cartão
    0.59
     कार्तिक
    0.57
    Theorem
    0.57
    ४
    0.57
    ۵
    0.57
     enligt
    0.56
    POSITIVE LOGITS
    in
    0.91
    v
    0.78
    at
    0.71
    n
    0.68
    al
    0.68
    i
    0.66
    nl
    0.65
    le
    0.64
    l
    0.62
    ene
    0.61
    Activations Density 0.000%

    No Known Activations