© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41825
    Prev
    Next
    INDEX
    Explanations

    storing possessions

    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_22_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
     мясо
    0.23
    Meat
    0.21
     прогу
    0.21
    隶
    0.21
     casually
    0.21
    meat
    0.21
    itudini
    0.20
     सेतु
    0.20
    Casual
    0.20
    ബ്ര
    0.20
    POSITIVE LOGITS
     Underground
    0.22
    仕
    0.21
     underground
    0.20
     combined
    0.20
     McK
    0.19
    transformed
    0.19
     POP
    0.18
    combined
    0.18
     Ronda
    0.18
     underneath
    0.18
    Activations Density 0.005%

    No Known Activations