© 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. 207146
    Prev
    Next
    INDEX
    Explanations

    In

    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
    月
    0.85
    월
    0.74
     월
    0.67
     月
    0.61
    月に
    0.53
     adet
    0.53
     maand
    0.53
     माह
    0.52
    月の
    0.52
     regl
    0.50
    POSITIVE LOGITS
     m
    1.58
     м
    1.27
     م
    1.09
    <0xA0>
    0.86
     म
    0.84
     ম
    0.79
    m
    0.77
    ม
    0.74
    𝑚
    0.71
     ம
    0.66
    Activations Density 0.001%

    No Known Activations