© 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
    2. Gemma-3-27B-IT
    3. 51-GEMMASCOPE-2-TRANSCODER-262K
    4. 67911
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
    atii
    0.46
     сма
    0.41
    lai
    0.40
    iaj
    0.40
    лая
    0.39
    尣
    0.39
    يه
    0.38
    ayah
    0.38
    ərə
    0.38
    yai
    0.38
    POSITIVE LOGITS
    킹
    0.44
    ক্ষ
    0.40
    kick
    0.40
     ach
    0.39
    чности
    0.39
    <0xA5>
    0.39
    que
    0.38
     Sicily
    0.38
    쾨
    0.38
    эк
    0.38
    Activations Density 0.010%

    No Known Activations