© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164371
    Prev
    Next
    INDEX
    Explanations

    chemical formulas

    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_13_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
     Cupertino
    0.54
     gloom
    0.54
    }|
    0.52
    ாடி
    0.50
     Color
    0.48
     Copper
    0.47
     Broccoli
    0.46
     teha
    0.46
     Alla
    0.46
     Glo
    0.46
    POSITIVE LOGITS
     अवशेष
    0.48
    entos
    0.47
    하십시오
    0.46
    cris
    0.46
    áveis
    0.45
    도
    0.45
    챌
    0.45
     اقسام
    0.44
    elses
    0.43
    발
    0.42
    Activations Density 0.001%

    No Known Activations