© 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. 134977
    Prev
    Next
    INDEX
    Explanations

    plagiarise, trivialise

    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
    m
    1.30
    st
    1.19
    م
    1.08
    ról
    1.05
    ರಣ
    1.03
     confronted
    1.02
     unfounded
    1.02
    lar
    1.01
    riever
    1.01
    کاری
    1.01
    POSITIVE LOGITS
    {
    1.52
    8
    1.27
    O
    1.22
    ти
    1.07
    China
    1.04
    Up
    1.03
     byla
    1.03
    U
    1.03
    At
    1.02
    Five
    1.02
    Activations Density 0.000%

    No Known Activations