© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251603
    Prev
    Next
    INDEX
    Explanations

    negative

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     uns
    0.45
    মিও
    0.41
    ֹ
    0.41
    mapping
    0.38
     p
    0.38
    翦
    0.37
     mape
    0.37
    prite
    0.37
     mapping
    0.37
     работы
    0.36
    POSITIVE LOGITS
     ridiculus
    0.44
     склада
    0.42
     WAY
    0.40
    Way
    0.38
    ော်
    0.38
    nt
    0.37
    週
    0.37
     week
    0.37
     giving
    0.37
     Weeks
    0.36
    Activations Density 0.002%

    No Known Activations