© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151126
    Prev
    Next
    INDEX
    Explanations

    script argument checks

    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_23_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
     ګټ
    0.52
     vendeurs
    0.43
    nie
    0.43
    vänd
    0.42
     vendeur
    0.41
     verkauft
    0.39
    轱
    0.39
    чы
    0.38
    atuur
    0.38
    有利于
    0.38
    POSITIVE LOGITS
    ENDPOINT
    0.40
    ান্তর
    0.39
    URNING
    0.36
    ஸ்ட்
    0.36
    ContentType
    0.36
     ประจํา
    0.35
    們
    0.35
    氘
    0.35
    ֛
    0.35
     alimentar
    0.35
    Activations Density 0.001%

    No Known Activations