© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162998
    Prev
    Next
    INDEX
    Explanations

    overflow-y: scroll; or auto;

    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_31_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
     Qatar
    0.41
    owls
    0.39
    ට
    0.39
     Los
    0.38
     Bot
    0.38
     Balt
    0.38
     Mechanical
    0.38
     Tolerance
    0.38
     Crafts
    0.37
    osynthesis
    0.37
    POSITIVE LOGITS
     अग्र
    0.40
    选举
    0.40
     encirc
    0.40
    MARKED
    0.39
     мин
    0.39
    போ
    0.39
    掻
    0.38
     accession
    0.38
     annunci
    0.38
     employee
    0.37
    Activations Density 0.002%

    No Known Activations