© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259037
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
     রকম
    0.73
    もので
    0.73
     Ausstattung
    0.71
     excel
    0.68
     उत्कृष्टता
    0.68
    яс
    0.67
    เลือก
    0.67
    ה
    0.66
     तरह
    0.65
     নির্বাচিত
    0.65
    POSITIVE LOGITS
     karm
    0.97
    
    0.82
     digested
    0.81
     tryptophan
    0.79
     foiled
    0.78
    肝
    0.78
    ✘
    0.78
     indigestion
    0.78
     dox
    0.78
     detectable
    0.78
    Activations Density 0.001%

    No Known Activations