© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104935
    Prev
    Next
    INDEX
    Explanations

    Old Town

    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_1_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
     $\
    1.37
     I
    1.31
     i
    1.30
     $
    1.29
    to
    1.26
     a
    1.20
     is
    1.17
     It
    1.16
    ти
    1.09
     _
    1.04
    POSITIVE LOGITS
    ين
    1.21
    ون
    1.05
    բ
    1.05
    ي
    1.02
    ன
    1.01
    ac
    0.97
    yre
    0.94
    σ
    0.94
    న్
    0.91
    ്രീ
    0.91
    Activations Density 0.003%

    No Known Activations