© 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. 88570
    Prev
    Next
    INDEX
    Explanations

    Playstation, Wegovy, C-states

    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
    etrically
    0.40
    ującego
    0.34
    <unused210>
    0.34
    ¹)
    0.34
    <unused199>
    0.34
    <unused1008>
    0.34
    ícím
    0.33
    ively
    0.33
    <unused510>
    0.32
     frecuentes
    0.32
    POSITIVE LOGITS
    ماش
    0.37
     Richmond
    0.36
     Peppers
    0.34
     lockers
    0.34
     B
    0.33
    0.32
     buns
    0.32
     bun
    0.32
     visor
    0.32
    C
    0.31
    Activations Density 0.012%

    No Known Activations