© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149540
    Prev
    Next
    INDEX
    Explanations

    choice selection options

    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_23_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
    jamin
    0.33
    uncak
    0.31
    klad
    0.31
    spra
    0.31
    ng
    0.30
     minim
    0.30
     gathered
    0.30
    ,-\
    0.30
    कमा
    0.30
    sum
    0.30
    POSITIVE LOGITS
     выбора
    0.50
     choisir
    0.49
     scegli
    0.49
     선택
    0.48
     lựa
    0.47
     выбира
    0.47
     scegliere
    0.47
     выборе
    0.46
    选择
    0.46
    可以选择
    0.44
    Activations Density 0.066%

    No Known Activations