© 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. 62526
    Prev
    Next
    INDEX
    Explanations

    Spanish 'mas' or 'mes'

    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
    та
    1.32
    u
    1.22
    x
    1.19
    त
    1.17
    ج
    1.15
    RI
    1.12
    g
    1.12
     раствор
    1.08
    et
    1.05
    ي
    1.05
    POSITIVE LOGITS
    টি
    0.97
    ür
    0.92
    서
    0.91
    人都
    0.84
    يل
    0.82
    ă
    0.82
     decentral
    0.79
    會
    0.79
    讧
    0.79
    annya
    0.78
    Activations Density 0.000%

    No Known Activations