© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201439
    Prev
    Next
    INDEX
    Explanations

    bare words and their suffixes

    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_12_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
     to
    0.58
    ！
    0.56
    𝑖
    0.56
    ＄
    0.53
    ،
    0.52
    ，
    0.52
    सी
    0.52
    is
    0.51
    pkg
    0.51
    ί
    0.51
    POSITIVE LOGITS
    en
    0.63
     raíces
    0.55
     timeCounter
    0.55
    AMAN
    0.54
     rapidamente
    0.53
    UpSync
    0.53
    xlim
    0.52
    alignat
    0.52
     MCSF
    0.50
     gaman
    0.50
    Activations Density 0.000%

    No Known Activations