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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202886
    Prev
    Next
    INDEX
    Explanations

    pop/popping

    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_46_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
     字
    0.43
    贤
    0.38
     Wallis
    0.37
     تضيفلها
    0.36
    ffect
    0.36
    никам
    0.36
     അനുഭവ
    0.36
    潘
    0.35
     adulter
    0.35
     adultery
    0.35
    POSITIVE LOGITS
     pop
    0.45
     Pop
    0.41
     கை
    0.41
    Pop
    0.40
     popping
    0.40
    pop
    0.38
     Pops
    0.38
     Crav
    0.38
    axiom
    0.37
     Lil
    0.36
    Activations Density 0.000%

    No Known Activations