© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232615
    Prev
    Next
    INDEX
    Explanations

    explaining or defining slang

    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_6_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
    म
    1.17
    ма
    1.14
    де
    1.13
    م
    1.12
    m
    1.09
     electrón
    1.07
    其他
    1.03
    ম
    1.02
    ă
    1.01
    મ
    1.00
    POSITIVE LOGITS
    er
    0.91
    ess
    0.83
     funziona
    0.83
    ol
    0.82
    .
    0.81
     moistur
    0.81
    ,.
    0.80
     channel
    0.80
     repellent
    0.79
    ิ
    0.79
    Activations Density 0.001%

    No Known Activations