© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9424
    Prev
    Next
    INDEX
    Explanations

    code and programming

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    .",
    1.34
    。",
    1.27
    .',
    1.23
    .],
    1.23
     。,
    1.21
     ।,
    1.20
    ."),
    1.15
    ."',
    1.14
    .),
    1.14
    ."],
    1.13
    POSITIVE LOGITS
     Pharmac
    0.74
     zelfs
    0.65
    æ
    0.63
     même
    0.63
     gdy
    0.62
    êtes
    0.62
     munt
    0.62
    ŭ
    0.61
     mesmo
    0.60
    ammation
    0.60
    Activations Density 1.691%

    No Known Activations