© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248052
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    Negative Logits
    too
    0.42
     too
    0.40
    –
    0.37
     deformation
    0.35
    ⓪
    0.35
    Tot
    0.34
    reo
    0.34
    astype
    0.34
    ]_
    0.33
    ↓
    0.33
    POSITIVE LOGITS
    던
    1.70
    하던
    1.53
     있던
    1.52
     كان
    1.04
     كانت
    1.02
     كانوا
    0.90
    كان
    0.89
     했던
    0.86
    했던
    0.80
     کان
    0.79
    Activations Density 0.000%

    No Known Activations