© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30761
    Prev
    Next
    INDEX
    Explanations

    damage or poor condition

    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
     layout
    0.41
    reth
    0.40
    layout
    0.40
    Wid
    0.40
    wid
    0.39
    汇
    0.39
     wiss
    0.38
    환
    0.38
     Layout
    0.37
    lemb
    0.37
    POSITIVE LOGITS
     deterior
    0.58
     deterioration
    0.54
     deteriorated
    0.54
     повре
    0.53
     deterioro
    0.53
     deteriorating
    0.51
    DAMAGE
    0.51
    损坏
    0.50
     dañ
    0.49
    损伤
    0.49
    Activations Density 0.012%

    No Known Activations