© 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
    2. Gemma-3-27B-IT
    3. 2-GEMMASCOPE-2-TRANSCODER-262K
    4. 159569
    Prev
    Next
    INDEX
    Explanations

    Durable

    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_2_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
     calent
    1.12
    ¹.
    1.11
     tradicion
    1.05
     sujet
    1.04
     naturais
    0.95
     creatividad
    0.93
     sensibilidad
    0.93
     legais
    0.93
     juríd
    0.92
    Р
    0.92
    POSITIVE LOGITS
    is
    1.56
    '
    1.10
    i
    1.08
    )
    1.02
    isinin
    0.98
    }
    0.96
     Islands
    0.94
    ר
    0.93
     Museum
    0.91
    ే
    0.90
    Activations Density 0.001%

    No Known Activations