© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196308
    Prev
    Next
    INDEX
    Explanations

    puns and wordplay

    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_27_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
    सीएफ
    0.39
    🫡
    0.38
     proteção
    0.38
     أف
    0.38
     безпе
    0.38
     madrugada
    0.37
    GFP
    0.36
     elettron
    0.36
     pihak
    0.36
     carab
    0.36
    POSITIVE LOGITS
    gène
    0.37
    ፥
    0.36
    ルド
    0.36
     Perhaps
    0.35
     Multiplication
    0.35
     Lond
    0.35
     Joh
    0.34
     존재하는
    0.34
     perhaps
    0.34
     Again
    0.34
    Activations Density 0.002%

    No Known Activations