© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 66124
    Prev
    Next
    INDEX
    Explanations

    /

    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
     kwargs
    0.40
     trailbl
    0.39
     Forschungs
    0.39
    チーム
    0.39
    線の
    0.39
     Teile
    0.39
     気
    0.38
    洮
    0.38
     ligne
    0.38
     lignes
    0.37
    POSITIVE LOGITS
    produced
    0.40
    ❞
    0.36
    Produced
    0.35
     Produced
    0.34
    _^
    0.34
    ilios
    0.33
     pet
    0.33
     touched
    0.33
     okolo
    0.33
    弄
    0.32
    Activations Density 0.000%

    No Known Activations