© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195558
    Prev
    Next
    INDEX
    Explanations

    alias and set commands

    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_26_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
    ೌ
    0.41
     Ше
    0.39
    oupe
    0.39
    ementara
    0.39
    té
    0.37
    aunque
    0.37
     ஆறு
    0.37
     நவீன
    0.36
    °.
    0.36
     Хи
    0.36
    POSITIVE LOGITS
    bois
    0.42
     tessel
    0.40
     gestation
    0.39
     cheap
    0.38
     pedals
    0.38
     interessant
    0.38
     foss
    0.36
     summits
    0.36
     mineralization
    0.35
     poisson
    0.35
    Activations Density 0.000%

    No Known Activations