© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140871
    Prev
    Next
    INDEX
    Explanations

    move up

    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_46_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
     held
    0.40
    бур
    0.40
     holds
    0.40
     持
    0.39
     schnell
    0.39
     سلام
    0.38
     quickly
    0.38
     hand
    0.38
    certs
    0.37
    онів
    0.37
    POSITIVE LOGITS
     up
    0.49
    起來
    0.43
    very
    0.42
    opium
    0.41
     upto
    0.40
     ಒ
    0.40
    VERY
    0.39
    Very
    0.39
    cho
    0.38
     Very
    0.37
    Activations Density 0.004%

    No Known Activations