© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161871
    Prev
    Next
    INDEX
    Explanations

    third parties

    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
    دين
    1.23
    دخل
    1.16
    daten
    1.11
    ⺊
    1.09
     bicicletas
    1.07
    욀
    1.07
    د
    1.06
     Chayin
    1.05
    Прави
    1.05
    دق
    1.05
    POSITIVE LOGITS
     in
    1.86
     It
    1.59
    도
    1.44
     In
    1.27
    c
    1.23
     The
    1.22
    ى
    1.22
    在
    1.16
    し
    1.13
     There
    1.08
    Activations Density 0.000%

    No Known Activations