© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52523
    Prev
    Next
    INDEX
    Explanations

    "So" followed by a phrase

    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_31_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
     so
    0.52
     So
    0.46
    so
    0.39
    So
    0.39
     уро
    0.33
     так
    0.32
     McIl
    0.32
     절
    0.32
    ltry
    0.31
     så
    0.31
    POSITIVE LOGITS
    ΡΑ
    0.39
    Conventional
    0.36
    шения
    0.36
     spiral
    0.35
    Reserved
    0.35
     monograph
    0.34
    Siempre
    0.34
    Always
    0.33
    eras
    0.33
     Conventional
    0.33
    Activations Density 0.001%

    No Known Activations