© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157702
    Prev
    Next
    INDEX
    Explanations

    specific names

    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_50_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
     XIX
    0.38
     Spam
    0.38
    ghis
    0.38
    덜
    0.38
    poi
    0.38
    etra
    0.38
     Elwood
    0.38
    anders
    0.37
     poi
    0.37
     Dewar
    0.37
    POSITIVE LOGITS
    Sach
    0.39
     Wo
    0.39
    𒊑
    0.38
     WHIT
    0.38
     सूत्रकृ
    0.38
    WO
    0.38
    [:-
    0.36
     ঋ
    0.36
    ր
    0.36
    ringstream
    0.36
    Activations Density 0.001%

    No Known Activations