© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30794
    Prev
    Next
    INDEX
    Explanations

    garage door

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     newTask
    0.41
     lar
    0.40
     вз
    0.38
    灘
    0.38
     lig
    0.37
     ظهر
    0.37
     definitive
    0.37
     lista
    0.36
     scene
    0.35
    νοντας
    0.35
    POSITIVE LOGITS
    门
    0.59
    Gate
    0.55
    gates
    0.55
    門
    0.55
    Doors
    0.52
    Gates
    0.50
    gate
    0.49
     Gate
    0.48
     gates
    0.48
    door
    0.47
    Activations Density 0.001%

    No Known Activations