© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85688
    Prev
    Next
    INDEX
    Explanations

    vestigial structures or private code

    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_18_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
     ECU
    0.54
    보
    0.53
    हेब
    0.52
    бор
    0.50
    혁
    0.49
    อ
    0.49
    뱀
    0.48
    웁
    0.47
     negócios
    0.47
    이
    0.47
    POSITIVE LOGITS
    ate
    0.54
     eignet
    0.48
    essing
    0.47
    illet
    0.46
    kate
    0.46
    tor
    0.45
    akot
    0.45
    igay
    0.44
    sti
    0.43
    akkhan
    0.43
    Activations Density 0.000%

    No Known Activations