© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89352
    Prev
    Next
    INDEX
    Explanations

    metaclass, prepare, mark, mutagen

    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_18_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
     could
    0.32
     melhorar
    0.31
    łąd
    0.31
     improves
    0.30
    隍
    0.29
    हाला
    0.29
    場面積
    0.29
     tentando
    0.28
     migliorare
    0.28
     cannot
    0.28
    POSITIVE LOGITS
    农民
    0.26
    第六
    0.26
     훨씬
    0.26
    深夜
    0.25
     FLA
    0.25
     በቀ
    0.24
    税务
    0.24
     بن
    0.24
    RPM
    0.24
    三
    0.24
    Activations Density 0.000%

    No Known Activations