© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220414
    Prev
    Next
    INDEX
    Explanations

    necessary

    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_31_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
    衰
    0.39
     లేదు
    0.36
    oyens
    0.35
    appen
    0.35
    وزی
    0.35
    的时
    0.35
     standpoint
    0.35
     estuvo
    0.33
     خانو
    0.33
    迸
    0.33
    POSITIVE LOGITS
     necessary
    0.79
    necessary
    0.73
     необходи
    0.73
     Necessary
    0.73
     nécessaire
    0.72
     nécessaires
    0.71
     необхід
    0.70
     necessário
    0.67
     szükséges
    0.67
     necesario
    0.66
    Activations Density 0.105%

    No Known Activations