© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34459
    Prev
    Next
    INDEX
    Explanations

    Unreal Engine

    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_3_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
    д
    0.76
    ä
    0.70
     uniques
    0.66
     uniq
    0.64
     Gaga
    0.62
     trigonometric
    0.61
     L
    0.59
     용
    0.59
     охорони
    0.59
     uniquely
    0.58
    POSITIVE LOGITS
    at
    0.82
    ك
    0.72
    প
    0.60
    UE
    0.58
    ere
    0.57
    NE
    0.57
    ZE
    0.57
    un
    0.56
    魄
    0.55
    EY
    0.55
    Activations Density 0.014%

    No Known Activations