© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13844
    Prev
    Next
    INDEX
    Explanations

    joining array elements

    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_13_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
     refinery
    0.53
    ↵↵↵
    0.50
     bertujuan
    0.50
    থর
    0.48
    refour
    0.48
    load
    0.48
    LD
    0.48
    aroos
    0.47
     המו
    0.47
    improve
    0.46
    POSITIVE LOGITS
     ana
    0.59
     Ngày
    0.59
    зі
    0.58
     Bör
    0.58
    V
    0.57
     Quelles
    0.56
     começ
    0.55
     Bene
    0.55
     Smiling
    0.55
     ἢ
    0.55
    Activations Density 0.003%

    No Known Activations