© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48401
    Prev
    Next
    INDEX
    Explanations

    修炼

    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
     be
    0.18
    铯
    0.17
     indictment
    0.17
    ون
    0.17
    aldb
    0.16
     its
    0.16
     있다면
    0.16
     చెందిన
    0.16
     ἢ
    0.15
     సంబంధించిన
    0.15
    POSITIVE LOGITS
    การ
    0.17
    K
    0.16
    9
    0.15
    ấn
    0.15
    ↵
    0.15
     và
    0.15
    )$.
    0.15
    IK
    0.15
    7
    0.15
    ม
    0.15
    Activations Density 0.034%

    No Known Activations