© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206821
    Prev
    Next
    INDEX
    Explanations

    complex text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     el
    3.08
     El
    2.95
    El
    2.83
     엘
    2.36
     Эль
    2.19
     EL
    2.14
    엘
    1.94
    <0x9D>
    1.93
    エル
    1.90
     elution
    1.80
    POSITIVE LOGITS
     たち
    0.35
    chetta
    0.34
     Adventures
    0.34
    șit
    0.33
     تنا
    0.32
     argue
    0.31
     Therm
    0.31
     کرد
    0.30
    ଟ
    0.30
     своим
    0.30
    Activations Density 0.011%

    No Known Activations