© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149641
    Prev
    Next
    INDEX
    Explanations

    sensory perception and comparison

    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_23_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
    γγρα
    0.25
    וד
    0.24
    Además
    0.23
    Residents
    0.23
    𝒶
    0.23
    NY
    0.22
    აზ
    0.22
    іб
    0.22
     angulis
    0.22
    Gujarat
    0.22
    POSITIVE LOGITS
     Aeronautics
    0.25
     Xan
    0.23
     Cassandra
    0.23
    0.21
     пот
    0.21
     суда
    0.21
     posible
    0.21
     뭐야
    0.21
     оказался
    0.21
     плане
    0.21
    Activations Density 0.007%

    No Known Activations