© 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. 111886
    Prev
    Next
    INDEX
    Explanations

    Redshift

    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
    يف
    1.19
    ق
    1.05
     внутрен
    1.01
     Мари
    0.98
    يرو
    0.98
     Сури
    0.97
    يان
    0.95
    ли
    0.95
    ер
    0.94
    }
    0.93
    POSITIVE LOGITS
    d
    1.66
    ik
    1.48
    b
    1.40
    w
    1.38
    u
    1.34
    t
    1.30
    ش
    1.29
    in
    1.27
    ni
    1.27
    et
    1.26
    Activations Density 0.001%

    No Known Activations