© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22016
    Prev
    Next
    INDEX
    Explanations

    sleep comfort items

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     pillow
    1.98
     pillows
    1.85
    pillow
    1.70
     cushions
    1.68
     Pillow
    1.67
     cushion
    1.63
     Cushion
    1.44
    枕
    1.42
     blankets
    1.26
     couch
    1.23
    POSITIVE LOGITS
    鶘
    0.38
    ্বে
    0.37
     jurisdict
    0.36
     கெல்
    0.35
    aupt
    0.34
     completeness
    0.34
    烃
    0.34
     reunir
    0.34
    çado
    0.34
    ከር
    0.33
    Activations Density 0.022%

    No Known Activations