© 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. 5154
    Prev
    Next
    INDEX
    Explanations

    a string of characters that looks like a hashed key

    oai_token-act-pair · gemini-2.0-flash

    code and file paths

    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
     R
    -1.38
     L
    -1.32
    R
    -1.20
    L
    -1.13
    <bos>
    -1.11
     T
    -1.02
     r
    -1.00
     S
    -0.93
     l
    -0.93
    r
    -0.90
    POSITIVE LOGITS
     >=",
    0.58
     חיצוניים
    0.56
     المعيارى
    0.53
     CÁ
    0.53
    fromnode
    0.52
     líquida
    0.51
     erk
    0.51
    amerikanischer
    0.51
     TAMBÉM
    0.51
    atino
    0.50
    Activations Density 37.259%

    No Known Activations