© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163921
    Prev
    Next
    INDEX
    Explanations

    break down the problem

    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
     gradually
    0.42
     Converting
    0.41
     друз
    0.40
    enderita
    0.39
    漸
    0.39
    hemeral
    0.39
     постепенно
    0.39
    只
    0.38
    rö
    0.38
    逐渐
    0.38
    POSITIVE LOGITS
    全國
    0.37
     structuring
    0.37
     사망
    0.35
    Weapon
    0.35
    认可
    0.35
     transactions
    0.34
     전국
    0.34
     legitimate
    0.34
    ளிர்
    0.34
    㐸
    0.34
    Activations Density 0.008%

    No Known Activations