© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201045
    Prev
    Next
    INDEX
    Explanations

    Terms of Service

    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_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
     când
    0.90
    葢
    0.88
    </h3>
    0.83
    ется
    0.82
     confine
    0.81
     mö
    0.80
     piè
    0.80
    าย
    0.80
    ิ่ง
    0.78
     freezing
    0.76
    POSITIVE LOGITS
    ptr
    1.12
    da
    1.08
    A
    1.05
    vors
    1.03
    1
    1.01
    ye
    1.00
    years
    1.00
    radians
    1.00
    ors
    0.98
    vb
    0.96
    Activations Density 0.000%

    No Known Activations