© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100010
    Prev
    Next
    INDEX
    Explanations

    pleasure, enjoyment, review followed by punctuation

    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_16_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
    WMat
    0.55
    ᇂ
    0.54
     emphasise
    0.53
     ສຳ
    0.53
     imprensa
    0.52
     criticise
    0.52
     erred
    0.52
    𝚃
    0.52
     yaptı
    0.51
     âmbito
    0.51
    POSITIVE LOGITS
     looming
    0.50
     .
    0.45
    <0x82>
    0.43
     Network
    0.43
     Mueller
    0.43
     Alternative
    0.43
    .?
    0.43
     Township
    0.43
     Brought
    0.43
    <0x91>
    0.42
    Activations Density 0.001%

    No Known Activations