© 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
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174557
    Prev
    Next
    INDEX
    Explanations

    titles:

    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
     Cerr
    0.40
     Yun
    0.38
     Rebels
    0.37
     School
    0.36
     Cant
    0.35
    iens
    0.35
     P
    0.35
     Trib
    0.35
     Cob
    0.35
     Belvedere
    0.35
    POSITIVE LOGITS
    병
    0.40
    preparing
    0.39
    Geschichte
    0.39
    Scandinavian
    0.39
    व्
    0.38
     vektor
    0.38
    Thin
    0.38
    Upgradeable
    0.37
     aident
    0.37
    ATTR
    0.37
    Activations Density 0.002%

    No Known Activations