© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201077
    Prev
    Next
    INDEX
    Explanations

    have

    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
    ణా
    0.43
     ঘ
    0.38
    iele
    0.38
    ura
    0.36
    翻
    0.36
     poll
    0.36
     speichern
    0.36
    poll
    0.36
    ślin
    0.35
    ponenten
    0.35
    POSITIVE LOGITS
     themselves
    0.46
     helmets
    0.42
     AudioClip
    0.40
     கொண்டனர்
    0.39
     সম্ভবত
    0.39
    درسة
    0.38
    ἆ
    0.37
    ństw
    0.37
     Ange
    0.37
     Paperback
    0.37
    Activations Density 0.002%

    No Known Activations