© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92224
    Prev
    Next
    INDEX
    Explanations

    local specialty ingredient context

    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
     치
    0.44
    <0x8C>
    0.44
    ects
    0.44
    immobil
    0.43
     Jillian
    0.43
    jek
    0.42
     विका
    0.42
    ujj
    0.41
     삼각형
    0.41
     बांध
    0.40
    POSITIVE LOGITS
    Лю
    0.57
    ނ
    0.57
    n
    0.55
     facilmente
    0.55
    ल
    0.55
     acepta
    0.54
     strumento
    0.54
     expose
    0.54
     ocupa
    0.53
    મ
    0.53
    Activations Density 0.000%

    No Known Activations