© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42603
    Prev
    Next
    INDEX
    Explanations

    low or zero interest rates

    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_22_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
    ুল্য
    0.41
     mantle
    0.39
     fences
    0.38
     parch
    0.38
     فری
    0.37
    გი
    0.36
    lenia
    0.36
    ₿
    0.36
     Flugh
    0.35
     poni
    0.35
    POSITIVE LOGITS
     определенных
    0.44
    यी
    0.43
    Certain
    0.40
     сот
    0.39
    <0x8F>
    0.39
    었던
    0.39
    嫉
    0.39
     certain
    0.38
    certain
    0.38
    obacter
    0.38
    Activations Density 0.002%

    No Known Activations