© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10931
    Prev
    Next
    INDEX
    Explanations

    phrase]. If there is not an example of personification, return nothing. Your response would look like RESPONSE = []. Sentence: "I have lots of pillows on my bed.actorworlds

    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
    land
    0.57
    ed
    0.53
    lands
    0.48
    dess
    0.47
    ↵↵
    0.47
    ous
    0.45
    ons
    0.44
    err
    0.44
    ?
    0.44
    god
    0.44
    POSITIVE LOGITS
    ﾞ
    0.52
     ಚುನ
    0.50
    িকাংশ
    0.48
    施工
    0.48
    Docket
    0.47
    Lors
    0.47
    Longueur
    0.47
    MktCap
    0.46
    NRC
    0.46
    Txt
    0.46
    Activations Density 0.000%

    No Known Activations