© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78455
    Prev
    Next
    INDEX
    Explanations

    say "ex"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     Ost
    0.43
    ồ
    0.38
    Ost
    0.37
     excepting
    0.37
    বৃত্ত
    0.35
     halaman
    0.35
    Observe
    0.35
     Edel
    0.34
    Rq
    0.34
     ost
    0.34
    POSITIVE LOGITS
     vý
    1.80
     Aus
    1.45
    Aus
    1.41
     Vý
    1.35
    Vý
    1.25
    출
    1.24
     xuất
    1.23
    vý
    1.21
     출
    1.14
     wy
    1.10
    Activations Density 0.070%

    No Known Activations