© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204825
    Prev
    Next
    INDEX
    Explanations

    conservation and restoration

    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_37_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
     productividad
    0.38
    Slash
    0.37
     النقطه
    0.37
     kumpulan
    0.36
    container
    0.36
    鵝
    0.36
    Quel
    0.35
    ("/");
    0.35
    సర
    0.35
    highscore
    0.35
    POSITIVE LOGITS
     conservation
    1.02
     Conservation
    0.99
     conserv
    0.96
    Conservation
    0.93
    conservation
    0.92
     conserved
    0.80
     conservación
    0.79
     konserv
    0.78
     Conserv
    0.77
     conserving
    0.75
    Activations Density 0.000%

    No Known Activations