© 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. 75335
    Prev
    Next
    INDEX
    Explanations

    numbers and code sequences

    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
     Corm
    0.40
     संजीव
    0.38
     सूर
    0.36
    ��������
    0.36
    atios
    0.36
    దిక
    0.35
     ruộng
    0.35
     Palmy
    0.34
    iyati
    0.34
    mobil
    0.34
    POSITIVE LOGITS
    Episode
    0.38
     liking
    0.37
    骊
    0.37
     exd
    0.36
     dû
    0.36
     curt
    0.35
     episodes
    0.35
    ွင့်
    0.34
     sepd
    0.34
    軻
    0.34
    Activations Density 0.001%

    No Known Activations