© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100357
    Prev
    Next
    INDEX
    Explanations

    turtle screen setup

    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_16_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
    <em>
    0.55
     destined
    0.53
     باشد
    0.52
    <strong>
    0.50
    ↵
    0.50
    и
    0.50
    だったら
    0.48
     svaki
    0.47
    哪个
    0.47
    术
    0.45
    POSITIVE LOGITS
    ᆼ
    0.57
     आउटफिट
    0.55
     Outfit
    0.55
    വിലെ
    0.53
    ᱶ
    0.52
    ennies
    0.52
    èques
    0.52
     telenov
    0.51
    attes
    0.50
     integrantes
    0.50
    Activations Density 0.002%

    No Known Activations