© 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. 197515
    Prev
    Next
    INDEX
    Explanations

    fit

    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
     disgraced
    0.35
    量は
    0.34
    不但
    0.34
     কারও
    0.33
     상
    0.33
    祇
    0.32
     अत्याधुनिक
    0.32
    岂
    0.32
    楓
    0.32
    τοι
    0.32
    POSITIVE LOGITS
    ung
    0.39
     nokt
    0.38
    ulas
    0.37
    ück
    0.36
    ipes
    0.35
    ì
    0.35
    yes
    0.34
     Tahiti
    0.34
    pes
    0.34
    +"
    0.34
    Activations Density 0.001%

    No Known Activations