© 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. 172876
    Prev
    Next
    INDEX
    Explanations

    grant management

    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
     रामानंद
    0.46
    蟹
    0.45
     үш
    0.44
     मानक
    0.42
    날
    0.42
    프트
    0.42
     モダン
    0.42
     APIDC
    0.41
    ナット
    0.39
     multiplic
    0.39
    POSITIVE LOGITS
    ing
    0.51
    e
    0.51
    atic
    0.49
    Tickets
    0.48
     beating
    0.48
    pe
    0.48
    es
    0.47
     of
    0.47
    ven
    0.46
    of
    0.46
    Activations Density 0.000%

    No Known Activations