© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237051
    Prev
    Next
    INDEX
    Explanations

    needed

    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_46_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
    要求
    0.37
     advis
    0.36
    ężczy
    0.35
    rame
    0.33
    require
    0.32
     Agu
    0.32
    abhave
    0.32
    📫
    0.32
     Nagoya
    0.32
     COc
    0.32
    POSITIVE LOGITS
     needed
    2.52
     Needed
    2.28
    needed
    2.23
    Needed
    2.11
     dibutuhkan
    1.66
     потрі
    1.60
    NEEDED
    1.52
     нужен
    1.48
     нужны
    1.46
     behö
    1.46
    Activations Density 0.001%

    No Known Activations