© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33151
    Prev
    Next
    INDEX
    Explanations

    shaping, being, reflecting, positions

    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
     inspirations
    0.44
     punto
    0.41
    潮
    0.37
    тия
    0.36
     мат
    0.36
    英寸
    0.36
     вдох
    0.36
     झग
    0.35
    Stride
    0.35
    trail
    0.35
    POSITIVE LOGITS
    ByCategory
    0.51
     discourse
    0.45
     exclude
    0.42
    पित
    0.40
     subjectivity
    0.40
    वत
    0.38
    讠
    0.38
    exclude
    0.38
     пространство
    0.38
     exclusion
    0.37
    Activations Density 0.061%

    No Known Activations