© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158444
    Prev
    Next
    INDEX
    Explanations

    zwenc, welch, wear, zwcad

    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
    s
    1.56
    in
    1.30
    is
    1.23
    ي
    1.23
    يان
    1.23
    ur
    1.22
    رى
    1.11
    го
    1.09
    وين
    1.09
    r
    1.08
    POSITIVE LOGITS
    을
    1.23
    야
    1.16
    ように
    1.13
     a
    1.12
    ↵
    1.08
    />
    1.08
     glomerular
    1.08
    )
    1.08
    ৮
    1.08
    لی
    1.05
    Activations Density 0.000%

    No Known Activations