© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90031
    Prev
    Next
    INDEX
    Explanations

    engineering colleges and goods

    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_11_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
     جوړونکی
    0.63
     നൂ
    0.61
    ㍉
    0.61
     trousers
    0.57
    ORIAL
    0.57
    ---’
    0.57
     pantalones
    0.56
     Tripathi
    0.56
    柤
    0.56
     rifi
    0.55
    POSITIVE LOGITS
    D
    0.65
    c
    0.62
     .
    0.61
    g
    0.59
     i
    0.58
    0.57
    S
    0.57
     D
    0.56
    "
    0.55
    x
    0.54
    Activations Density 0.001%

    No Known Activations