© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138736
    Prev
    Next
    INDEX
    Explanations

    mathematics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    lays
    0.45
    ष्क
    0.42
    ྵ
    0.41
    റ്റ്‌വർ
    0.40
    存
    0.39
     lays
    0.38
    ilai
    0.38
     inseparable
    0.37
    ത്സ
    0.37
    সংস
    0.36
    POSITIVE LOGITS
    ウド
    0.43
     पर्यंत
    0.40
     Be
    0.39
    Be
    0.38
    Тер
    0.38
    glide
    0.38
    держа
    0.37
    炮
    0.37
     Canonical
    0.37
    canon
    0.36
    Activations Density 0.000%

    No Known Activations