© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34493
    Prev
    Next
    INDEX
    Explanations

    names ending in Jr

    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_7_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
    al
    1.16
    ।
    0.97
    ală
    0.87
    لة
    0.86
    ls
    0.85
    lamak
    0.84
    kład
    0.83
    adati
    0.83
    ricanes
    0.82
    ль
    0.81
    POSITIVE LOGITS
    의
    0.90
    ের
    0.90
    s
    0.84
    ی
    0.82
    の
    0.81
    的
    0.80
    u
    0.79
    </b>
    0.78
    ﺔ
    0.77
    </h2>
    0.77
    Activations Density 0.001%

    No Known Activations