© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90277
    Prev
    Next
    INDEX
    Explanations

    feeling of tightness

    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_11_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
     worsening
    0.45
     predicted
    0.44
    এছ
    0.44
     potent
    0.42
     anticipated
    0.42
    イ
    0.42
     assertions
    0.41
     chipped
    0.41
    اش
    0.41
     affective
    0.40
    POSITIVE LOGITS
     ܡ
    0.59
     ragazza
    0.54
     ننوت
    0.54
     meravigli
    0.54
     vengono
    0.53
     gigantes
    0.52
     transduction
    0.51
     جارہ
    0.51
    kfollowers
    0.50
     चुप
    0.50
    Activations Density 0.000%

    No Known Activations