© 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
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81535
    Prev
    Next
    INDEX
    Explanations

    reviews of websites or products

    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_0_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
    م
    1.80
    ب
    1.77
    ס
    1.70
    ल
    1.50
    па
    1.41
    ले
    1.37
    ன
    1.30
    ק
    1.29
    ش
    1.26
    б
    1.23
    POSITIVE LOGITS
    -
    1.71
    1
    1.55
    та
    1.52
    :
    1.38
    é
    1.38
    um
    1.35
    0
    1.30
    ü
    1.23
    érapie
    1.22
    ter
    1.19
    Activations Density 0.000%

    No Known Activations