© 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. 108111
    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_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
     have
    1.47
    s
    1.38
     has
    1.20
     on
    1.13
     (
    1.10
    する
    1.08
    كان
    1.07
    的
    1.00
     was
    0.98
     Have
    0.98
    POSITIVE LOGITS
    ן
    1.30
    i
    1.13
    "
    1.13
    ്യ
    1.06
    رد
    1.06
    ;
    1.05
     privilégi
    1.00
    "};
    0.98
    ش
    0.98
    ین
    0.96
    Activations Density 0.000%

    No Known Activations