© 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. 201303
    Prev
    Next
    INDEX
    Explanations

    desechar, deseado, deseable

    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
     Со
    0.99
    </h2>
    0.98
     اليمن
    0.96
     Ди
    0.96
    wirk
    0.93
    ре
    0.92
    ен
    0.89
     Ευ
    0.89
     Сара
    0.89
    ੰ
    0.89
    POSITIVE LOGITS
    i
    1.48
    as
    1.29
    o
    1.28
    u
    1.25
    in
    1.17
    is
    1.16
    y
    1.13
    p
    1.11
    at
    1.10
    ا
    1.02
    Activations Density 0.000%

    No Known Activations