© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39317
    Prev
    Next
    INDEX
    Explanations

    DevOps services and consulting

    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_3_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
    л
    0.86
    ulares
    0.72
    м
    0.71
    д
    0.71
    of
    0.70
    ﺪ
    0.66
    ation
    0.62
    um
    0.61
     sustancias
    0.61
    ೀರ
    0.59
    POSITIVE LOGITS
    a
    0.70
     analyser
    0.65
    [];
    0.63
    ه
    0.62
    י
    0.60
     feminino
    0.59
    ;
    0.59
    বিদ
    0.59
    が出来
    0.58
     oxidase
    0.58
    Activations Density 0.001%

    No Known Activations