© 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. 89365
    Prev
    Next
    INDEX
    Explanations

    instantly followed by effect

    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
    l
    1.01
    G
    0.89
    im
    0.89
    v
    0.87
    o
    0.84
    t
    0.81
    zahlung
    0.79
    h
    0.75
    c
    0.74
    pa
    0.73
    POSITIVE LOGITS
    )
    0.68
     dicembre
    0.61
     kojim
    0.60
     lega
    0.58
    ები
    0.57
    )。
    0.56
    <0x80>
    0.55
    рія
    0.55
     rant
    0.55
     térmica
    0.55
    Activations Density 0.001%

    No Known Activations