© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219271
    Prev
    Next
    INDEX
    Explanations

    open

    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_47_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
    دت
    0.43
    atah
    0.38
    uda
    0.38
     Уда
    0.37
    鹈
    0.37
     કા
    0.36
    preis
    0.36
    ጲ
    0.36
     buttons
    0.36
     DS
    0.36
    POSITIVE LOGITS
    aceis
    0.40
     vált
    0.38
     modifying
    0.38
    iera
    0.38
    gone
    0.38
    Manus
    0.38
     spoken
    0.37
    marque
    0.37
    laces
    0.37
    MODIFY
    0.36
    Activations Density 0.002%

    No Known Activations