© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156890
    Prev
    Next
    INDEX
    Explanations

    Veyron, Shenron

    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_2_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
     by
    1.27
    IC
    1.16
    l
    1.16
    RI
    1.05
    اي
    1.01
    t
    1.01
    Z
    1.01
    larda
    0.99
    RA
    0.98
    ли
    0.97
    POSITIVE LOGITS
    س
    1.42
    د
    1.23
    ι
    1.12
    า
    1.09
    ות
    1.05
     elution
    1.04
     infliction
    0.98
    㨁
    0.98
     incision
    0.97
    و
    0.96
    Activations Density 0.001%

    No Known Activations