© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13245
    Prev
    Next
    INDEX
    Explanations

    math formulas and variable symbols

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PDR
    -0.47
     ویکی‌پدیای
    -0.44
     Sedgwick
    -0.43
     PD
    -0.42
     SPAR
    -0.41
     päiv
    -0.40
    SD
    -0.40
    SDG
    -0.40
    ässä
    -0.40
    delwed
    -0.39
    POSITIVE LOGITS
     BT
    0.88
    Ht
    0.87
    Bt
    0.85
    Ot
    0.85
     MT
    0.85
     Gt
    0.84
    Gt
    0.83
     RT
    0.82
     Ot
    0.82
     GT
    0.81
    Activations Density 11.348%

    No Known Activations