© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87140
    Prev
    Next
    INDEX
    Explanations

    academic journals

    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_3_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
    یم
    0.79
    ми
    0.75
    ार
    0.72
    لی
    0.71
    न्स
    0.66
     Воло
    0.66
    칵
    0.66
    ং
    0.66
    عی
    0.65
    чі
    0.65
    POSITIVE LOGITS
     and
    0.66
     be
    0.61
     not
    0.61
    January
    0.59
     لأ
    0.59
            
    0.59
     February
    0.58
     و
    0.55
     f
    0.55
     ف
    0.55
    Activations Density 0.000%

    No Known Activations