© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241692
    Prev
    Next
    INDEX
    Explanations

    on or in the

    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_25_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
    طبيق
    0.40
    ləşdir
    0.39
     témoins
    0.39
    meniz
    0.38
     Context
    0.38
    শাক
    0.38
    ņem
    0.37
    禎
    0.37
    hdfs
    0.36
     सम्मान
    0.36
    POSITIVE LOGITS
     type
    0.45
     caterpillar
    0.41
    ":
    0.39
     directly
    0.38
     Asphalt
    0.38
     diretamente
    0.38
     cramped
    0.38
     three
    0.37
    olica
    0.37
     sheet
    0.37
    Activations Density 0.003%

    No Known Activations