© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12725
    Prev
    Next
    INDEX
    Explanations

    Rodgers, Rogers, Hector, Stam, Mont

    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
    oxys
    0.45
    ಕಾ
    0.43
     服
    0.42
    寤
    0.41
    ervasyon
    0.40
     served
    0.39
     Nomin
    0.39
    MathML
    0.38
     кафе
    0.38
    増加
    0.38
    POSITIVE LOGITS
     Rodgers
    0.35
     Stam
    0.35
    ('',
    0.35
     Sow
    0.35
     Rogers
    0.34
    Fleet
    0.34
    凤
    0.33
     Hector
    0.33
    StackNavigator
    0.33
     Mont
    0.33
    Activations Density 0.001%

    No Known Activations