© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225424
    Prev
    Next
    INDEX
    Explanations

    affection, affections, affectionately

    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_10_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
    ر
    0.40
    ing
    0.38
    ле
    0.37
    ين
    0.35
    이스
    0.34
    艨
    0.34
    u
    0.33
    ب
    0.32
    ન
    0.32
     poderá
    0.32
    POSITIVE LOGITS
    .
    0.45
    </b>
    0.26
    \.
    0.26
     f
    0.25
     bank
    0.25
     drug
    0.24
    तक
    0.24
    ↵
    0.23
     l
    0.23
    น่า
    0.23
    Activations Density 0.001%

    No Known Activations