© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60653
    Prev
    Next
    INDEX
    Explanations

    reservations required or essential

    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_2_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
    ون
    1.22
     on
    1.20
    র
    1.17
     are
    1.16
    ا
    1.14
    ้
    1.14
    י
    1.11
     och
    1.10
    ब
    1.09
    هم
    1.08
    POSITIVE LOGITS
    nieuw
    1.16
    да
    1.12
    ların
    1.07
    га
    1.06
    oną
    1.06
     в
    1.03
    يره
    1.03
     maliciously
    1.03
    ﺪ
    1.03
    st
    1.02
    Activations Density 0.002%

    No Known Activations