© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18809
    Prev
    Next
    INDEX
    Explanations

    arrival; time

    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
     NA
    0.40
     going
    0.39
     republika
    0.39
     Asante
    0.37
     republic
    0.37
     Going
    0.36
    Going
    0.35
    ଧ
    0.35
     fuego
    0.34
     hautes
    0.34
    POSITIVE LOGITS
     arrive
    0.82
     arrived
    0.79
     arrives
    0.79
     arriva
    0.77
     arriver
    0.71
     arrival
    0.70
     arrivée
    0.69
     arriving
    0.68
     arriv
    0.67
     llega
    0.67
    Activations Density 0.056%

    No Known Activations