© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200457
    Prev
    Next
    INDEX
    Explanations

    mass

    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
     cru
    0.47
    campo
    0.44
     unnecessarily
    0.43
     selfishness
    0.41
    田
    0.40
     લો
    0.39
    npmjs
    0.39
     brutally
    0.38
    timing
    0.37
     VRS
    0.37
    POSITIVE LOGITS
    Ward
    0.41
    گے
    0.41
    ូវ
    0.41
     বক্তব
    0.38
     Société
    0.38
    כות
    0.37
    ulfonic
    0.37
    ikes
    0.37
    ⇠
    0.37
    addWidget
    0.36
    Activations Density 0.001%

    No Known Activations