© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23407
    Prev
    Next
    INDEX
    Explanations

    drive or ride

    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_56_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
     Mutual
    0.42
    Mutual
    0.39
    ګ
    0.37
     trad
    0.37
    NaOH
    0.37
     вза
    0.36
    жением
    0.36
     morning
    0.35
    🥑
    0.35
    Blind
    0.35
    POSITIVE LOGITS
     drives
    1.57
     Drives
    1.42
     dri
    1.03
    rives
    0.75
     ride
    0.70
     props
    0.63
     rides
    0.62
     driv
    0.59
     Ride
    0.58
     ड्राइव
    0.58
    Activations Density 0.051%

    No Known Activations