© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 68194
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.5-flash-lite

    specific named entities, often locations or organizations, along with descriptive terms.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
     Welsh
    0.45
     सल
    0.44
     வெள்ள
    0.40
     storms
    0.39
    鰍
    0.38
     My
    0.37
     flowing
    0.37
    Ҭ
    0.37
    썸
    0.37
     Net
    0.36
    POSITIVE LOGITS
    Alph
    0.39
    La
    0.37
    Chicago
    0.37
    راحة
    0.37
     Pavlov
    0.37
    Passport
    0.37
    தூ
    0.37
     Gait
    0.37
    dds
    0.36
     લા
    0.36
    Activations Density 0.007%

    No Known Activations