© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14615
    Prev
    Next
    INDEX
    Explanations

    historical context and impact

    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_15_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
    iales
    0.20
     .
    0.19
    ins
    0.17
    ossil
    0.17
    im
    0.17
     besuchte
    0.16
    年に
    0.16
    uramente
    0.16
    院长
    0.16
    <strong>
    0.16
    POSITIVE LOGITS
    字典
    0.20
     kiu
    0.19
     চুলের
    0.19
     నేను
    0.19
     nő
    0.18
     దూ
    0.18
     wonderland
    0.18
     bookArray
    0.18
     tatu
    0.18
     marad
    0.18
    Activations Density 0.047%

    No Known Activations