© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134662
    Prev
    Next
    INDEX
    Explanations

    tldr and explain

    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_1_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
    s
    2.09
    ים
    1.74
    ের
    1.46
    ों
    1.46
    ς
    1.41
    ม
    1.41
     on
    1.39
    ના
    1.39
    sa
    1.38
    ات
    1.36
    POSITIVE LOGITS
    i
    1.19
    <0x80>
    1.16
    fromi
    1.14
    bindingFields
    1.10
     zwią
    1.07
    iunea
    1.05
    n
    1.04
     realiz
    1.02
    ᱐
    1.02
     γιατί
    1.00
    Activations Density 0.000%

    No Known Activations