© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38895
    Prev
    Next
    INDEX
    Explanations

    leaving or going

    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_11_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
    >
    0.67
    et
    0.61
    {
    0.58
    $
    0.58
    it
    0.56
        
    0.56
    Large
    0.55
    t
    0.54
    Er
    0.53
    \
    0.53
    POSITIVE LOGITS
    𒂍
    0.51
    ಾಟ
    0.49
    ंचित
    0.48
     undertook
    0.47
     originals
    0.46
     undertakes
    0.46
     reaffirmed
    0.45
     exodus
    0.45
     diseased
    0.44
     próprios
    0.44
    Activations Density 0.030%

    No Known Activations