© 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
    2. Gemma-3-27B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 130966
    Prev
    Next
    INDEX
    Explanations

    billions of stars

    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_25_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
    }($
    0.44
    ្ម
    0.38
     Peak
    0.37
    set
    0.37
    idé
    0.37
     peak
    0.37
     handmade
    0.37
     aiuta
    0.36
     set
    0.36
     ACID
    0.36
    POSITIVE LOGITS
     ciel
    0.39
    冕
    0.39
     Twentieth
    0.37
     Jessica
    0.36
    ่วม
    0.35
    نے
    0.35
     ponctuées
    0.34
    ającą
    0.34
    𝘽
    0.34
    posición
    0.34
    Activations Density 0.004%

    No Known Activations