© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10427
    Prev
    Next
    INDEX
    Explanations

    "teh" and cats

    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_13_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
    頎
    0.40
    𝜆
    0.40
    ΙΚ
    0.39
     পরিস্কার
    0.39
    𝑺
    0.37
    𝓙
    0.37
    ಗೊಳ
    0.37
    ्रोल
    0.36
    不一樣
    0.36
     एकड़
    0.36
    POSITIVE LOGITS
    t
    0.36
    ">
    0.33
    ere
    0.33
     </
    0.33
     feline
    0.33
    .
    0.33
     +
    0.33
     fans
    0.32
     believers
    0.32
    c
    0.32
    Activations Density 0.046%

    No Known Activations