© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 153819
    Prev
    Next
    INDEX
    Explanations

    how to do something

    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_60_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
    …?
    0.38
     ਕੁ
    0.37
     outset
    0.35
     Am
    0.34
     использования
    0.33
     ?
    0.33
     Arg
    0.33
     Mes
    0.32
     ¶
    0.32
     Ness
    0.32
    POSITIVE LOGITS
    lower
    0.50
    have
    0.50
    Have
    0.49
     lower
    0.49
    Lower
    0.48
    Gain
    0.47
     have
    0.45
     stabilise
    0.45
    Bring
    0.44
     won
    0.44
    Activations Density 0.001%

    No Known Activations