© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109949
    Prev
    Next
    INDEX
    Explanations

    Judeo-Christian heritage

    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_2_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
    ing
    1.17
     for
    1.13
    ية
    1.07
    ة
    1.00
    eur
    0.97
    o
    0.91
    ik
    0.89
    iden
    0.85
    ens
    0.84
    a
    0.84
    POSITIVE LOGITS
    ש
    1.16
    स
    1.02
    ত
    0.92
    その
    0.91
    ために
    0.90
    স
    0.84
    ເຄື່ອງ
    0.84
    ޏ
    0.84
    સ
    0.80
    א
    0.80
    Activations Density 0.000%

    No Known Activations