© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67844
    Prev
    Next
    INDEX
    Explanations

    Hamburg

    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_46_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
     Pari
    0.42
     pary
    0.41
    Corr
    0.39
    IND
    0.39
     pSig
    0.38
     Monitors
    0.38
     Cort
    0.38
    僥
    0.37
     cort
    0.37
     pard
    0.37
    POSITIVE LOGITS
     Hamburg
    1.32
    Hamburg
    1.30
     Hamburger
    1.16
     hamburg
    1.14
     Hamb
    1.13
    Hamburger
    1.13
     hamburger
    1.01
    hamburger
    0.97
     HAM
    0.95
     Bremen
    0.94
    Activations Density 0.001%

    No Known Activations