© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39855
    Prev
    Next
    INDEX
    Explanations

    contentious debate or issue

    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_11_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
    ünüz
    0.66
    UM
    0.65
    )}^{\
    0.64
    ;
    0.64
    ऎ
    0.63
    <unused2156>
    0.63
    стров
    0.63
     slows
    0.62
    bucks
    0.61
    ୯
    0.61
    POSITIVE LOGITS
    el
    0.75
    0.71
     tecla
    0.70
    ed
    0.66
     finalizar
    0.61
     critic
    0.61
     θέση
    0.61
     ίδια
    0.59
     severe
    0.59
    েকে
    0.57
    Activations Density 0.003%

    No Known Activations