© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207418
    Prev
    Next
    INDEX
    Explanations

    bearing, quickly, Jewels, active

    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_20_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
     dangerous
    0.51
     gefähr
    0.51
     criminal
    0.49
     dangereux
    0.47
     automática
    0.46
     сист
    0.44
    Dangerous
    0.44
    萄
    0.43
     safegu
    0.42
    rawberry
    0.42
    POSITIVE LOGITS
     बेसिक
    0.45
     Tage
    0.45
    BO
    0.44
    zero
    0.43
    histor
    0.43
    兴
    0.43
    depth
    0.42
    empty
    0.42
    함
    0.42
    𝚖
    0.42
    Activations Density 0.000%

    No Known Activations