© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207880
    Prev
    Next
    INDEX
    Explanations

    for

    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
     soziale
    0.18
     hohe
    0.17
     immedi
    0.17
     เบ
    0.17
     সদ
    0.17
    FRINGEMENT
    0.17
     ס
    0.17
    으
    0.16
    Autom
    0.16
    ஸ்த
    0.16
    POSITIVE LOGITS
     conviction
    0.18
     Epic
    0.17
    bicara
    0.17
     puck
    0.16
    を楽し
    0.16
     metr
    0.16
     idéal
    0.16
    চর্
    0.16
     tutor
    0.16
     discussions
    0.15
    Activations Density 0.001%

    No Known Activations