© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9445
    Prev
    Next
    INDEX
    Explanations

    code annotations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     नी
    0.72
    怯
    0.71
    জ্জ
    0.69
    гор
    0.69
     साइट
    0.68
    rightsquigarrow
    0.67
     निर्देशन
    0.67
     kemungkinan
    0.67
     प्रमाणात
    0.66
    彿
    0.66
    POSITIVE LOGITS
     @
    0.90
    @
    0.81
     Tomato
    0.72
     at
    0.72
    Tomato
    0.66
     స్ట
    0.64
     tomato
    0.63
     Sel
    0.61
    テル
    0.61
    \@
    0.61
    Activations Density 0.001%

    No Known Activations