© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167871
    Prev
    Next
    INDEX
    Explanations

    gentle actions with understanding

    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_34_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
     brace
    0.40
    豁
    0.37
     trophy
    0.36
     सबकुछ
    0.36
    λογή
    0.35
     glanced
    0.35
     recycling
    0.34
     dilihat
    0.34
    erland
    0.34
     nhìn
    0.34
    POSITIVE LOGITS
     gentle
    0.47
    belongs
    0.45
     Gentle
    0.44
    擬
    0.44
    挼
    0.40
     gently
    0.39
     Gently
    0.39
     Interview
    0.38
    gent
    0.38
     cloth
    0.38
    Activations Density 0.005%

    No Known Activations