© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 213455
    Prev
    Next
    INDEX
    Explanations

    library client code

    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_43_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
    蠟
    0.38
     seats
    0.37
     SwitchCompat
    0.36
     బో
    0.35
     plomb
    0.34
     Gear
    0.34
     Seats
    0.34
     smother
    0.34
     Bled
    0.34
     sitting
    0.33
    POSITIVE LOGITS
    OUND
    0.41
     nicer
    0.38
    abb
    0.37
    Farmer
    0.37
    秾
    0.37
     hsize
    0.36
     Farming
    0.36
    தேச
    0.36
     less
    0.36
    keme
    0.36
    Activations Density 0.000%

    No Known Activations