© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214853
    Prev
    Next
    INDEX
    Explanations

    mixed data fragments

    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_50_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
    ־
    0.46
    ermark
    0.45
    -
    0.43
    об
    0.42
    рожден
    0.41
    ປະກ
    0.41
    eseed
    0.40
    стра
    0.40
    ಬ
    0.40
    ವಾರ
    0.39
    POSITIVE LOGITS
    nae
    0.38
    jha
    0.38
    স্থ
    0.37
    uation
    0.37
    스와
    0.37
    ():
    0.37
    jective
    0.37
    འི་
    0.36
    &&
    0.36
     commune
    0.36
    Activations Density 0.147%

    No Known Activations