© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 34614
    Prev
    Next
    INDEX
    Explanations

    comunicación científica multidimensional

    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_31_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
     birdie
    0.27
     linking
    0.25
     ścian
    0.25
    埄
    0.25
     monotonous
    0.25
     occupied
    0.24
     كنت
    0.24
    Caut
    0.24
    ূত
    0.24
     enkelt
    0.24
    POSITIVE LOGITS
    rais
    0.25
     prosecute
    0.24
    ))=\
    0.23
    }}=\
    0.22
    मोल
    0.22
     тер
    0.22
    }}+\
    0.22
    oderm
    0.22
    alahan
    0.21
    alang
    0.21
    Activations Density 0.007%

    No Known Activations