© 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. 9465
    Prev
    Next
    INDEX
    Explanations

    or

    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
     constitutes
    0.72
     precedes
    0.70
     ensures
    0.69
     comprises
    0.66
     depicts
    0.65
     optimizes
    0.65
     cannot
    0.64
     置
    0.64
     characterizes
    0.63
     understands
    0.63
    POSITIVE LOGITS
    หรือ
    0.81
     ወይም
    0.75
    或
    0.74
     లేదా
    0.74
    든지
    0.73
    :
    0.72
     ಅಥವಾ
    0.71
    irmeye
    0.70
     или
    0.70
    :-
    0.68
    Activations Density 0.012%

    No Known Activations