© 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. 5145
    Prev
    Next
    INDEX
    Explanations

    causes and contributions

    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
     happening
    0.40
     Shared
    0.40
     仮
    0.39
     sociedad
    0.38
     મદદ
    0.35
    িশ
    0.35
    modified
    0.35
     Hunter
    0.35
    society
    0.35
     SET
    0.34
    POSITIVE LOGITS
     致
    0.43
     contribute
    0.43
     contribuer
    0.43
     contributed
    0.42
     contrib
    0.42
     contribuir
    0.40
     عامل
    0.40
     اهلا
    0.38
     Contribute
    0.38
     contribution
    0.37
    Activations Density 0.176%

    No Known Activations