© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 197054
    Prev
    Next
    INDEX
    Explanations

    certain types

    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_9_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
    म
    0.52
     estructura
    0.51
     Ingeniería
    0.51
     línea
    0.48
    contenedor
    0.48
    फ्टर
    0.48
     ingeniero
    0.48
     trabajo
    0.47
    थे
    0.47
     ahí
    0.47
    POSITIVE LOGITS
    ’
    0.55
    jacking
    0.47
     demarcation
    0.45
    的
    0.45
     violation
    0.42
     framing
    0.42
     使用
    0.41
    uning
    0.41
    alupe
    0.41
    primitive
    0.41
    Activations Density 0.000%

    No Known Activations