© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2065
    Prev
    Next
    INDEX
    Explanations

    templating blocks followed by keywords

    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_39_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
    營
    0.43
    subarray
    0.43
     Continuing
    0.43
    जून
    0.39
    อล
    0.39
     प्रभावी
    0.38
    tolist
    0.38
     चै
    0.38
    ব্যা
    0.38
    ocar
    0.38
    POSITIVE LOGITS
     empty
    0.56
    empty
    0.51
     Empty
    0.50
    Empty
    0.48
    空
    0.48
     空
    0.41
    空的
    0.40
    ظمة
    0.40
    ...),
    0.39
     EMPTY
    0.38
    Activations Density 0.001%

    No Known Activations