© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35627
    Prev
    Next
    INDEX
    Explanations

    places and transportation

    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_11_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
    ਪਣ
    0.21
    ponible
    0.20
     같이
    0.20
    moveTo
    0.20
    hava
    0.19
    newLine
    0.19
     볼
    0.18
    hér
    0.18
    फ्त
    0.18
    seqNum
    0.18
    POSITIVE LOGITS
    ר
    0.21
    ولا
    0.20
    ନ
    0.19
     функції
    0.18
    ייה
    0.18
    uliert
    0.18
    ฮ
    0.18
    留
    0.18
    ли
    0.17
    ือก
    0.17
    Activations Density 0.003%

    No Known Activations