© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207656
    Prev
    Next
    INDEX
    Explanations

    say currency codes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    $，
    0.38
    \$
    0.37
    前面的
    0.34
     شرطونه
    0.33
     Rs
    0.33
    $\
    0.33
     배경
    0.33
     RTP
    0.32
     Padres
    0.32
    ⁧
    0.32
    POSITIVE LOGITS
     attorno
    0.49
    around
    0.49
     around
    0.48
    Around
    0.45
     Around
    0.44
     alrededor
    0.38
     intorno
    0.36
     cca
    0.35
    ="("
    0.35
     autour
    0.33
    Activations Density 0.002%

    No Known Activations