© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210941
    Prev
    Next
    INDEX
    Explanations

    unit or sequence

    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_20_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
     для
    0.40
     για
    0.36
     よ
    0.36
     für
    0.36
    eka
    0.35
     parte
    0.35
    )(
    0.35
    )/
    0.34
     for
    0.34
    anjutan
    0.34
    POSITIVE LOGITS
    حديث
    0.44
    ธุ
    0.39
    মিত
    0.38
    Session
    0.37
    session
    0.36
    വ്ര
    0.35
    দ্র
    0.35
     Missions
    0.34
    حدة
    0.34
     세제곱
    0.34
    Activations Density 0.008%

    No Known Activations