© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230762
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    ς
    1.05
    ה
    1.04
    ی
    1.03
    К
    1.02
    ן
    0.98
    ມັນ
    0.96
    ຜະລິດຕະພັນ
    0.96
    ם
    0.92
    ל
    0.92
    ஸ்
    0.91
    POSITIVE LOGITS
    o
    1.12
    -
    1.09
    0.87
    et
    0.86
    College
    0.82
    ad
    0.82
     meadow
    0.82
    asjon
    0.82
     gennem
    0.78
    oS
    0.77
    Activations Density 0.000%

    No Known Activations