© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199368
    Prev
    Next
    INDEX
    Explanations

    bangkok, body, or title

    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_9_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
    ам
    0.54
    ુ
    0.53
    оти
    0.50
    描
    0.50
    ામ
    0.48
    ünkü
    0.47
    тип
    0.47
    м
    0.47
    дового
    0.46
    тим
    0.46
    POSITIVE LOGITS
     NCT
    0.49
     for
    0.48
    gaard
    0.46
     NIH
    0.45
    eber
    0.45
     écr
    0.44
     rowing
    0.44
    frank
    0.43
     crystall
    0.43
     culminating
    0.43
    Activations Density 0.000%

    No Known Activations