© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200680
    Prev
    Next
    INDEX
    Explanations

    terraform providers

    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_12_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
    isiä
    0.55
     regrett
    0.54
    刄
    0.53
     Ελλά
    0.52
    จำเป็น
    0.52
     seas
    0.51
    の名前
    0.51
     Seas
    0.50
     arguments
    0.49
    éis
    0.49
    POSITIVE LOGITS
    are
    0.55
    waitFor
    0.55
    con
    0.53
    l
    0.50
    can
    0.49
    commun
    0.48
    גר
    0.47
    und
    0.47
    чу
    0.46
    <0xE3>
    0.46
    Activations Density 0.015%

    No Known Activations