© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145269
    Prev
    Next
    INDEX
    Explanations

    questions and inspiration

    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_0_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
     וה
    1.36
    Y
    1.36
     nostre
    1.30
    gawa
    1.30
    ELL
    1.22
    O
    1.22
    AL
    1.20
     explicabo
    1.18
     ένα
    1.17
     मिलकर
    1.17
    POSITIVE LOGITS
    s
    1.87
    ные
    1.45
    és
    1.32
    ৫
    1.32
    satz
    1.30
    ى
    1.29
    د
    1.28
    t
    1.24
    是
    1.23
    ség
    1.23
    Activations Density 0.000%

    No Known Activations