© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45270
    Prev
    Next
    INDEX
    Explanations

    left byleft vacantleft behind

    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_13_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
     Phenomenology
    0.33
    ޯ
    0.32
    pragma
    0.32
    وندی
    0.32
    мене
    0.31
    lengths
    0.31
    Ằ
    0.31
     Dirección
    0.31
    marriage
    0.31
    мости
    0.31
    POSITIVE LOGITS
     unle
    0.30
    ard
    0.29
    珍惜
    0.29
     lessen
    0.29
    ച്ചത്
    0.28
    ü
    0.27
     superstar
    0.27
    InsertInt
    0.27
    ە
    0.27
     débat
    0.26
    Activations Density 0.007%

    No Known Activations