© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112807
    Prev
    Next
    INDEX
    Explanations

    intimate connection

    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_2_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
    ார்
    1.34
    upta
    1.05
    ри
    1.03
    s
    1.03
    soldiers
    0.98
    urts
    0.93
    erin
    0.91
    ן
    0.91
     Иң
    0.90
    ᇂ
    0.90
    POSITIVE LOGITS
    ः
    1.14
    ：
    1.08
     transportar
    1.03
    لی
    1.02
    د
    0.98
    ac
    0.97
    ق
    0.97
    uk
    0.93
     pengertian
    0.93
    .
    0.93
    Activations Density 0.000%

    No Known Activations