© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171774
    Prev
    Next
    INDEX
    Explanations

    list items and quotes

    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_20_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
    ung
    0.21
     Foro
    0.21
    ી
    0.21
     Ian
    0.21
     iOS
    0.21
     νέ
    0.21
    aná
    0.21
     Entity
    0.21
    |(
    0.20
    práv
    0.20
    POSITIVE LOGITS
     modesty
    0.24
    两次
    0.21
     چاہ
    0.20
    Trying
    0.20
    MenuStyle
    0.20
     கதாபா
    0.20
    Chats
    0.20
     überprü
    0.19
    挎
    0.19
    **,
    0.19
    Activations Density 0.001%

    No Known Activations