© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 763
    Prev
    Next
    INDEX
    Explanations

    tunnels

    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_44_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
     slate
    0.40
    ],$
    0.39
    slate
    0.38
     ഗുരു
    0.38
     १२
    0.37
     തുട
    0.36
    маты
    0.36
     gai
    0.36
     réduit
    0.35
    緘
    0.35
    POSITIVE LOGITS
     Tunnel
    0.48
     tunnel
    0.46
    Tunnel
    0.46
     tunnels
    0.45
    Tune
    0.42
    tunnel
    0.42
    Ether
    0.42
     ETH
    0.41
    unnel
    0.41
    隧道
    0.41
    Activations Density 0.007%

    No Known Activations