© 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. 42340
    Prev
    Next
    INDEX
    Explanations

    open orders, open fires, open seams, open market, open source, open Guest, open ID, open Savannah, open positions

    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
    c
    0.49
    an
    0.46
     impresion
    0.43
     resto
    0.42
    າດ
    0.42
    ्रे
    0.42
    ো
    0.41
    og
    0.41
    he
    0.40
    žu
    0.40
    POSITIVE LOGITS
    baiki
    0.40
     ।*
    0.39
     wäre
    0.39
    ।*
    0.38
     menghilangkan
    0.38
    </strong>
    0.38
    បង្ហ
    0.38
    }^{*}
    0.38
    eko
    0.37
    destroyEach
    0.37
    Activations Density 0.029%

    No Known Activations