© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221815
    Prev
    Next
    INDEX
    Explanations

    this or open + descriptor

    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_10_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
    ене
    0.50
    är
    0.38
    ités
    0.36
    (
    0.35
    وس
    0.35
    isión
    0.34
    ابت
    0.34
    ه
    0.34
    یز
    0.34
    isp
    0.33
    POSITIVE LOGITS
     on
    0.39
     la
    0.38
     le
    0.38
     l
    0.38
     ל
    0.38
     ณ
    0.38
    tu
    0.37
     estoy
    0.37
     ある
    0.37
     don
    0.37
    Activations Density 0.010%

    No Known Activations