© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9266
    Prev
    Next
    INDEX
    Explanations

    component object model COM

    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_13_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
    6
    0.71
    ｎ
    0.63
     টিকিট
    0.55
     ৬
    0.55
     confessions
    0.55
    ci
    0.54
     caramel
    0.54
     quarterfinals
    0.54
     ܘ
    0.53
     കണ്ണ
    0.53
    POSITIVE LOGITS
    创建
    0.56
     forwarding
    0.56
    town
    0.52
     الص
    0.51
    use
    0.50
     crear
    0.50
    ము
    0.50
    енти
    0.49
    사용
    0.48
    霝
    0.48
    Activations Density 0.014%

    No Known Activations