© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8940
    Prev
    Next
    INDEX
    Explanations

    evoked potentials and averaging

    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_13_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
    g
    0.58
    p
    0.55
     g
    0.54
    t
    0.54
    ’)
    0.52
    å
    0.50
     j
    0.50
     quando
    0.49
    v
    0.49
     in
    0.48
    POSITIVE LOGITS
     行っ
    0.57
    نی
    0.55
    ዪ
    0.55
    EL
    0.54
     আয়নগুলির
    0.54
     کی
    0.53
     አይደለም
    0.53
    Ⅹ
    0.52
     सर्विसेज
    0.51
    表达式
    0.50
    Activations Density 0.007%

    No Known Activations