© 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. 34929
    Prev
    Next
    INDEX
    Explanations

    AI assistant interaction

    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
    ifício
    0.42
     altamente
    0.41
    édé
    0.40
    érapie
    0.37
    ▷
    0.36
    ྭ
    0.36
     highly
    0.35
    Had
    0.35
    ͇
    0.35
    yscy
    0.35
    POSITIVE LOGITS
     saan
    0.38
    さり
    0.38
    rán
    0.35
     Pfe
    0.35
    leid
    0.35
    たり
    0.34
    સ્પ
    0.34
     Kum
    0.34
    conten
    0.34
    ंसर
    0.34
    Activations Density 1.068%

    No Known Activations