© 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. 156909
    Prev
    Next
    INDEX
    Explanations

    agrarian

    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
    is
    1.31
    ن
    1.31
    ores
    1.16
    ere
    1.13
    นิด
    1.10
    ethe
    1.09
    isn
    1.09
    ICK
    1.05
    ع
    1.05
    }"
    1.03
    POSITIVE LOGITS
     to
    1.82
    ，
    1.49
    好
    1.16
    ка
    1.13
    多
    1.13
    ﺍ
    1.09
    ット
    1.07
    ،
    1.06
     (
    1.05
    高清
    1.05
    Activations Density 0.000%

    No Known Activations