© 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. 144307
    Prev
    Next
    INDEX
    Explanations

    name endings like -öhn or -uhn

    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
    ۰
    1.71
    ia
    1.58
    ai
    1.58
    า
    1.45
    0
    1.41
    lor
    1.39
    lerin
    1.24
    riot
    1.21
    ०
    1.21
     I
    1.20
    POSITIVE LOGITS
    ми
    1.73
    '
    1.68
    в
    1.64
    র
    1.56
    N
    1.53
    ر
    1.52
    "
    1.47
    し
    1.46
    L
    1.42
    र
    1.39
    Activations Density 0.000%

    No Known Activations