© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54122
    Prev
    Next
    INDEX
    Explanations

    postal service and mail delivery

    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_30_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
     বণিক
    0.30
     curving
    0.27
    orylation
    0.27
     multicellular
    0.27
    spectral
    0.26
    ᓄ
    0.26
    ুগত্য
    0.26
     colaborador
    0.26
     recombination
    0.26
     mols
    0.26
    POSITIVE LOGITS
     Postal
    0.31
     postal
    0.28
     USPS
    0.28
     >>
    0.26
    Postal
    0.26
     ✅
    0.25
    邮
    0.24
    wyczaj
    0.24
     register
    0.24
     Register
    0.24
    Activations Density 0.001%

    No Known Activations