© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44886
    Prev
    Next
    INDEX
    Explanations

    committee decisions and ethical review

    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_13_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
     neuropathy
    0.47
     connective
    0.44
     reduce
    0.44
     싶
    0.43
    ራት
    0.41
     prevent
    0.41
     apps
    0.41
    encije
    0.41
    HALL
    0.40
     alleviate
    0.40
    POSITIVE LOGITS
    êmica
    0.48
     Approval
    0.43
     jî
    0.42
     mwen
    0.42
    льні
    0.41
     criança
    0.41
    iciaire
    0.41
    冻
    0.41
    மி
    0.41
     jovem
    0.41
    Activations Density 0.020%

    No Known Activations