© 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. 140700
    Prev
    Next
    INDEX
    Explanations

    ost

    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
    ஞ
    0.43
    襦
    0.43
    Ryan
    0.41
    Online
    0.38
    غان
    0.37
     Practices
    0.37
     practices
    0.36
    olutely
    0.36
     pratiques
    0.36
     Implementing
    0.35
    POSITIVE LOGITS
     ceded
    0.41
    туру
    0.41
    锰
    0.41
    DEFG
    0.40
    क्साइड
    0.40
     (_.
    0.39
     oxidase
    0.37
    ೇವ
    0.37
     Sha
    0.36
    метр
    0.36
    Activations Density 0.001%

    No Known Activations