© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9107
    Prev
    Next
    INDEX
    Explanations

    research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ل
    1.59
     kanamycin
    1.21
    ו
    1.16
     atth
    1.13
    लया
    1.08
    āyaṇa
    1.07
     possibilidade
    1.05
    𝕦
    1.04
    Keyword
    1.04
     airson
    1.03
    POSITIVE LOGITS
     ingress
    1.21
     mezzo
    1.08
     partis
    0.98
     altos
    0.95
     antigos
    0.94
     खासा
    0.93
     presa
    0.91
     arsenal
    0.90
    bildung
    0.90
     bleeding
    0.90
    Activations Density 0.006%

    No Known Activations