© 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-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202878
    Prev
    Next
    INDEX
    Explanations

    end of Python code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     bý
    0.44
     pourquoi
    0.38
    잣
    0.36
     whip
    0.36
     ধর্ষ
    0.36
     pá
    0.35
    ât
    0.34
     Pai
    0.34
    âts
    0.34
     FileReader
    0.33
    POSITIVE LOGITS
    following
    0.46
     nums
    0.44
    骼
    0.44
     seguintes
    0.43
    Popen
    0.43
     seguenti
    0.40
     following
    0.40
    """
    0.39
     следующие
    0.38
    lanan
    0.38
    Activations Density 0.003%

    No Known Activations