© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116138
    Prev
    Next
    INDEX
    Explanations

    critically evaluate

    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_27_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
     निशुल्क
    0.45
     रुच
    0.42
     Societe
    0.41
     первая
    0.41
    梂
    0.41
     сначала
    0.41
    逑
    0.41
    ьому
    0.40
    雔
    0.40
    学部
    0.40
    POSITIVE LOGITS
     inc
    0.43
    ze
    0.41
     gl
    0.39
     |
    0.39
    ben
    0.38
    é
    0.37
    “
    0.37
    ab
    0.36
     te
    0.36
     attén
    0.36
    Activations Density 0.001%

    No Known Activations