© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29869
    Prev
    Next
    INDEX
    Explanations

    KL divergence and power loss

    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_40_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
     nervous
    0.46
    ノ
    0.46
    䈤
    0.40
    нова
    0.40
    クション
    0.39
    落
    0.38
    Understand
    0.38
    nore
    0.38
     Nervous
    0.38
    ८
    0.38
    POSITIVE LOGITS
    渺
    0.42
     Ts
    0.40
     recept
    0.40
     dř
    0.40
    árl
    0.39
     stá
    0.39
     Ried
    0.39
    蝉
    0.38
    ार्टमेंट
    0.37
     öss
    0.37
    Activations Density 0.008%

    No Known Activations