© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201758
    Prev
    Next
    INDEX
    Explanations

    ideology in various contexts

    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_6_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
    to
    1.08
    нат
    0.92
     exacta
    0.90
     є
    0.90
     devad
    0.90
    b
    0.89
    то
    0.89
     особа
    0.88
     меня
    0.88
     ожида
    0.85
    POSITIVE LOGITS
    I
    1.24
     are
    1.22
     an
    1.15
    場合は
    1.13
    ick
    1.10
     have
    1.03
    </strong>
    1.00
    ica
    0.97
    ला
    0.94
    ità
    0.94
    Activations Density 0.002%

    No Known Activations