© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240019
    Prev
    Next
    INDEX
    Explanations

    testing, testing, testing

    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_25_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
     Field
    0.38
     സോഷ്യ
    0.38
     необходимые
    0.38
    灭
    0.38
     Geological
    0.37
    私は
    0.37
    riques
    0.37
    私の
    0.37
     рекомендуется
    0.37
     Kok
    0.37
    POSITIVE LOGITS
     megaphone
    0.40
     jurídica
    0.37
     camshaft
    0.37
     automaton
    0.36
    ivided
    0.36
     despertar
    0.35
     đ
    0.35
    看出
    0.35
     suitcases
    0.35
    ifizieren
    0.34
    Activations Density 0.000%

    No Known Activations