© 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. 257513
    Prev
    Next
    INDEX
    Explanations

    well-regarded

    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
    illion
    0.43
    毀
    0.40
     харак
    0.40
     anymore
    0.40
     VIR
    0.39
    uka
    0.39
    }`;
    0.38
    ko
    0.38
     Godwin
    0.38
     LIVE
    0.38
    POSITIVE LOGITS
     futebol
    0.43
     tuition
    0.42
     grill
    0.41
     proletariat
    0.40
    Liberal
    0.39
     don
    0.38
    viä
    0.38
     resumes
    0.38
     tacit
    0.37
     fonctions
    0.37
    Activations Density 0.005%

    No Known Activations