© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98165
    Prev
    Next
    INDEX
    Explanations

    UwU speak

    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_14_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
     С
    0.42
    的手
    0.42
    ഗീയ
    0.42
     practicar
    0.41
     prototyp
    0.40
    杳
    0.40
     и
    0.39
     Kurz
    0.39
     Europea
    0.39
     व
    0.38
    POSITIVE LOGITS
    ynucle
    0.61
     businesses
    0.50
     attraction
    0.50
    enium
    0.49
    offers
    0.48
    த்தை
    0.47
     restoration
    0.47
     Abia
    0.47
     оюндары
    0.47
    ajem
    0.46
    Activations Density 0.000%

    No Known Activations