© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 129804
    Prev
    Next
    INDEX
    Explanations

    that/which I

    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_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
    gown
    0.36
     ję
    0.36
     nudity
    0.35
     whore
    0.35
    міна
    0.33
    瀞
    0.33
     nic
    0.32
     ngôn
    0.32
    ibly
    0.32
    weichen
    0.32
    POSITIVE LOGITS
     pís
    0.38
    тали
    0.37
     ‌
    0.37
    hern
    0.37
    朩
    0.36
     tions
    0.35
     నాలుగు
    0.35
    タンク
    0.35
     Bắc
    0.35
    AnimationClip
    0.35
    Activations Density 0.005%

    No Known Activations