© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 21715
    Prev
    Next
    INDEX
    Explanations

    names

    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
     thought
    0.41
    astore
    0.40
     pensato
    0.38
     गणेश
    0.38
    ANGMAR
    0.38
    against
    0.37
    瞭
    0.37
     thoughts
    0.37
    =(-
    0.37
     हेल्पलाइन
    0.36
    POSITIVE LOGITS
     Jo
    0.46
    E
    0.44
     E
    0.42
     Kerk
    0.41
     ریز
    0.41
     Las
    0.41
     LAS
    0.40
    Jo
    0.40
     김
    0.40
     kass
    0.39
    Activations Density 0.004%

    No Known Activations