© 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. 66076
    Prev
    Next
    INDEX
    Explanations

    its

    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
     perny
    0.40
    )}(\
    0.38
    ருக்கும்
    0.37
    깎
    0.36
     ос
    0.36
     ။
    0.36
    ర్లు
    0.36
     싶
    0.36
    ሬ
    0.36
     योजनाओं
    0.35
    POSITIVE LOGITS
     its
    0.53
    mathml
    0.47
    heres
    0.45
     someth
    0.44
     unrealistic
    0.44
     disrespectful
    0.44
    Its
    0.44
    احت
    0.43
     missing
    0.42
     here
    0.42
    Activations Density 0.004%

    No Known Activations