© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 43848
    Prev
    Next
    INDEX
    Explanations

    .js

    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
    eraj
    0.22
     zgodnie
    0.21
    erweise
    0.20
    kimi
    0.20
    k
    0.20
    kurs
    0.19
    当然
    0.19
     parece
    0.19
     Part
    0.19
     secondo
    0.19
    POSITIVE LOGITS
    OLYBDENUM
    0.20
    సుకొ
    0.20
    ()+"
    0.19
     pobl
    0.18
     tabletop
    0.18
    ทำงาน
    0.18
     иск
    0.18
    স
    0.17
    ())).
    0.17
    ()));
    0.17
    Activations Density 0.023%

    No Known Activations