© 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. 50990
    Prev
    Next
    INDEX
    Explanations

    "IA", "DA", "FA"

    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
    meetings
    0.37
     প্লাট
    0.36
    నో
    0.35
    ണമെന്ന്
    0.35
    甚
    0.35
     ಕ್ಷೇತ್ರದ
    0.33
    主
    0.33
    Glad
    0.33
    翱
    0.33
    తే
    0.32
    POSITIVE LOGITS
     DA
    0.41
     SNA
    0.41
    FAI
    0.40
    FAs
    0.38
    Ẫ
    0.38
    FA
    0.38
     geophysical
    0.38
     JA
    0.37
     FA
    0.37
    ipramine
    0.36
    Activations Density 0.000%

    No Known Activations