© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10756
    Prev
    Next
    INDEX
    Explanations

    cerca, cavour, cante

    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_40_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
    +.
    0.38
     Abo
    0.38
    霜
    0.37
    شته
    0.36
    +")
    0.35
     réf
    0.35
    Dealing
    0.35
     Dubey
    0.35
    炎
    0.35
     defences
    0.34
    POSITIVE LOGITS
     food
    0.42
    food
    0.42
    ("#{
    0.38
     makanan
    0.37
     காற்றின்
    0.36
     knock
    0.36
    ৩১
    0.36
     рабочей
    0.36
     grease
    0.35
    ṓ
    0.35
    Activations Density 0.026%

    No Known Activations