© 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. 59343
    Prev
    Next
    INDEX
    Explanations

    cryptocurrencies, altcoins

    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
    し
    1.67
    ni
    1.37
    l
    1.31
    ни
    1.29
    м
    1.25
    ৫
    1.23
    К
    1.20
    jší
    1.15
    sw
    1.13
     I
    1.13
    POSITIVE LOGITS
     are
    1.33
     was
    1.09
    é
    1.08
    ючи
    1.00
     can
    0.99
     fungicide
    0.99
     dicho
    0.98
     in
    0.96
    きました
    0.96
     histó
    0.96
    Activations Density 0.000%

    No Known Activations