© 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. 258136
    Prev
    Next
    INDEX
    Explanations

    chemical structures and reactions

    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
    രുടെ
    0.45
    ণ্ঠে
    0.43
    ιά
    0.41
     candlest
    0.41
     ހ
    0.40
    dued
    0.39
    avourite
    0.39
     اظہار
    0.39
     doby
    0.39
    ፈ
    0.39
    POSITIVE LOGITS
    eco
    0.42
    cleaning
    0.38
     層
    0.37
    경
    0.37
    污染
    0.36
    CNN
    0.36
    ektir
    0.36
    作り
    0.36
     Stet
    0.36
    transform
    0.35
    Activations Density 0.001%

    No Known Activations