© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35398
    Prev
    Next
    INDEX
    Explanations

    well-deserved and well-suited

    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_7_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
     two
    0.89
    د
    0.89
     were
    0.81
    ari
    0.78
     was
    0.73
     time
    0.71
     by
    0.70
     δύο
    0.69
     }
    0.68
     one
    0.68
    POSITIVE LOGITS
    ין
    0.83
    מ
    0.82
     veineux
    0.78
    ми
    0.77
    ين
    0.76
    ان
    0.74
    м
    0.71
    姆斯
    0.71
    трон
    0.70
    ה
    0.69
    Activations Density 0.000%

    No Known Activations