© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116719
    Prev
    Next
    INDEX
    Explanations

    team performance and records

    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_27_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
     غلام
    0.40
     різних
    0.35
     न्यायिक
    0.35
    罡
    0.34
    rbrakk
    0.34
    )}{(
    0.33
     Equitable
    0.33
    ⌛
    0.33
     VALUES
    0.33
    놋
    0.33
    POSITIVE LOGITS
    writeObject
    0.38
    पने
    0.38
     отношение
    0.37
     fazem
    0.37
     cai
    0.35
    ppet
    0.35
    tokenizer
    0.35
    ugar
    0.35
     expres
    0.34
    atto
    0.34
    Activations Density 0.000%

    No Known Activations