© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45018
    Prev
    Next
    INDEX
    Explanations

    covered in moss or other substances

    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_22_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
    ifact
    0.42
     marital
    0.41
    aktif
    0.40
     BEING
    0.40
    이죠
    0.40
    
    0.39
    ामु
    0.38
    🧠
    0.38
    📵
    0.38
    Drinking
    0.38
    POSITIVE LOGITS
     Jan
    0.45
     rivers
    0.45
     Lauderdale
    0.45
     大
    0.44
     Αυ
    0.43
     напол
    0.43
    带宽
    0.42
     parede
    0.42
     đại
    0.42
     speechless
    0.42
    Activations Density 0.004%

    No Known Activations