© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44625
    Prev
    Next
    INDEX
    Explanations

    Unspecified characters and code snippets

    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_3_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
     ultimate
    0.70
    ม
    0.70
    ส
    0.67
    ות
    0.64
    会
    0.64
     and
    0.63
     independ
    0.63
    ื้อง
    0.63
     administrar
    0.61
    เขา
    0.60
    POSITIVE LOGITS
    大
    0.74
     \
    0.67
    рили
    0.66
    arey
    0.63
    }$,
    0.63
    ك
    0.63
    ارية
    0.62
     ايجاد
    0.61
    }$.
    0.61
    {\
    0.60
    Activations Density 0.018%

    No Known Activations