© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106130
    Prev
    Next
    INDEX
    Explanations

    KL Divergence and monkeys

    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_1_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
    :
    1.68
    이나
    1.16
    }
    1.12
    *
    1.07
    ↵
    1.02
    is
    1.02
    ，
    1.00
    )
    0.99
    ,
    0.98
    л
    0.97
    POSITIVE LOGITS
    𝟏
    1.32
    f
    1.16
    ır
    1.16
    ૧
    1.16
    1
    1.09
     from
    1.07
    し
    1.05
    した
    1.05
    ری
    1.03
    कारात्मक
    1.03
    Activations Density 0.000%

    No Known Activations