© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63454
    Prev
    Next
    INDEX
    Explanations

    institutions and statistics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     y
    2.64
    <0xA1>
    1.57
     य
    1.47
     ی
    1.46
     ي
    1.38
     Y
    1.29
     ய
    1.27
    ｙ
    1.20
    y
    1.19
     ya
    1.17
    POSITIVE LOGITS
    Pis
    0.41
     pis
    0.41
     there
    0.40
     Pis
    0.38
     সেখানে
    0.37
     वहां
    0.36
    AllFilesIn
    0.36
     allí
    0.36
    queleto
    0.36
    ಕಿ
    0.35
    Activations Density 0.009%

    No Known Activations