© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33877
    Prev
    Next
    INDEX
    Explanations

    moves on

    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_7_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
     başlayalım
    0.40
    श
    0.37
     फीट
    0.36
    하루
    0.35
    រ
    0.34
    ил
    0.33
    ्ट
    0.33
    n
    0.33
    𝕣
    0.33
    сных
    0.33
    POSITIVE LOGITS
     was
    0.53
     =
    0.50
     an
    0.49
     is
    0.49
     a
    0.45
    י
    0.44
     it
    0.41
    '
    0.41
     the
    0.39
     are
    0.39
    Activations Density 0.001%

    No Known Activations