© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210833
    Prev
    Next
    INDEX
    Explanations

    encuestas electorales

    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_5_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
     is
    1.06
    ني
    1.01
    kontrol
    0.91
     Га
    0.90
    kf
    0.89
    να
    0.89
    льним
    0.88
     ล
    0.87
    kker
    0.87
     UEFA
    0.86
    POSITIVE LOGITS
    IN
    1.27
    )
    1.16
    1
    1.14
    ]
    1.13
    _
    1.08
    \%
    1.07
    هما
    1.07
    '
    1.05
    )'
    1.00
    ı
    0.97
    Activations Density 0.000%

    No Known Activations