© 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. 90020
    Prev
    Next
    INDEX
    Explanations

    a lot more than

    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
    اك
    0.81
    то
    0.67
    دين
    0.64
    х
    0.63
    ين
    0.62
     يد
    0.60
     لجنة
    0.59
    ());
    0.59
    ቃል
    0.58
    са
    0.57
    POSITIVE LOGITS
    ।
    0.82
    I
    0.81
    Ε
    0.73
    。
    0.69
    Ι
    0.67
    are
    0.66
    A
    0.61
    이었
    0.60
    着
    0.60
    Ξ
    0.59
    Activations Density 0.000%

    No Known Activations