© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148929
    Prev
    Next
    INDEX
    Explanations

    factoring quadratic equations

    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_23_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
    駆動
    0.42
    ulose
    0.41
     patriarch
    0.41
     atributos
    0.41
    ྣ
    0.40
     rasgos
    0.40
     компонен
    0.40
    驅
    0.39
    َة
    0.39
     mappa
    0.39
    POSITIVE LOGITS
    oggles
    0.41
     cheers
    0.40
    operatorname
    0.38
     minimize
    0.38
     normalize
    0.38
     }$
    0.38
    近日
    0.38
     afe
    0.35
    !!
    0.35
     demanding
    0.35
    Activations Density 0.000%

    No Known Activations