© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14838
    Prev
    Next
    INDEX
    Explanations

    room EQ modes size analog devices computers

    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_13_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
     Б
    0.15
    茉
    0.15
    물
    0.13
    с
    0.13
    制
    0.13
    ле
    0.13
    比较
    0.13
    又は
    0.13
     plen
    0.13
    ін
    0.13
    POSITIVE LOGITS
     ellos
    0.17
    ToDO
    0.15
    orghini
    0.14
     lover
    0.14
     ductile
    0.14
     permitido
    0.14
    ethoven
    0.14
    on
    0.14
     illa
    0.14
     teller
    0.13
    Activations Density 0.002%

    No Known Activations