© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13498
    Prev
    Next
    INDEX
    Explanations

    the word "multi" and words connected by a hyphen

    oai_token-act-pair · gemini-2.0-flash

    multi

    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
     HasFactory
    -0.54
    amerikan
    -0.48
    principalColumn
    -0.48
    <bos>
    -0.47
     OFDb
    -0.47
    出版年
    -0.46
     onAnimation
    -0.46
     AssemblyProduct
    -0.45
     Wicidata
    -0.45
     metav
    -0.45
    POSITIVE LOGITS
    awtextra
    0.66
    Carreira
    0.63
    sima
    0.58
    ture
    0.57
    kloped
    0.56
    슷
    0.56
    IndentedString
    0.54
    menta
    0.54
    MemoryWarning
    0.52
     referrerpolicy
    0.52
    Activations Density 6.012%

    No Known Activations