© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97181
    Prev
    Next
    INDEX
    Explanations

    take the lead in

    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_14_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
    อก
    0.31
    客服
    0.30
    ජ
    0.29
    UK
    0.28
     Operator
    0.27
     interviewer
    0.27
    able
    0.27
     London
    0.27
    '
    0.27
     operator
    0.27
    POSITIVE LOGITS
    流域
    0.28
     photons
    0.28
    ا
    0.26
    ি
    0.26
    Ongoing
    0.26
     кого
    0.26
    امہ
    0.26
     наука
    0.26
    ongi
    0.25
     overtake
    0.25
    Activations Density 0.002%

    No Known Activations