© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35954
    Prev
    Next
    INDEX
    Explanations

    charges

    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_11_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
    6
    0.68
     Роб
    0.61
    acil
    0.60
    :&
    0.59
    Payments
    0.59
    OGRAP
    0.58
    LLDB
    0.58
    8
    0.58
    wagon
    0.56
    PEG
    0.56
    POSITIVE LOGITS
    ing
    0.67
    يان
    0.58
    ار
    0.57
    েরই
    0.57
     kürz
    0.57
    庿
    0.57
    ての
    0.56
    取的
    0.55
    খানি
    0.55
    o
    0.55
    Activations Density 0.000%

    No Known Activations