© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31295
    Prev
    Next
    INDEX
    Explanations

    are some or are the

    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_31_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
     быстрее
    0.40
    Clock
    0.39
     নিশ্চিত
    0.39
    Answer
    0.38
     গিয়েছে
    0.38
    containsKey
    0.37
     logra
    0.37
    ใ
    0.36
    simx
    0.36
     backside
    0.36
    POSITIVE LOGITS
    chett
    0.41
     Ched
    0.40
    anking
    0.38
    estones
    0.38
    chart
    0.37
    aning
    0.36
     বিরাট
    0.36
     example
    0.36
     voorbeeld
    0.36
    ushima
    0.36
    Activations Density 0.007%

    No Known Activations