© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57467
    Prev
    Next
    INDEX
    Explanations

    compound word beginnings

    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_59_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
     B
    0.48
     N
    0.44
     A
    0.43
     In
    0.42
    In
    0.38
    Sono
    0.38
     P
    0.38
     His
    0.38
    Saya
    0.38
     C
    0.37
    POSITIVE LOGITS
     pulsation
    0.43
     estren
    0.43
     prostatitis
    0.41
     gamanam
    0.40
     nirvach
    0.39
     teritor
    0.39
     enfermed
    0.38
     renfer
    0.38
     endometri
    0.38
     scrutin
    0.38
    Activations Density 0.047%

    No Known Activations