© 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. 15563
    Prev
    Next
    INDEX
    Explanations

    angle brackets enclosing text with numbers and letters

    oai_token-act-pair · 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
     tartalomajánló
    -0.78
    lieger
    -0.68
    SharedDtor
    -0.67
     '\\;'
    -0.66
    UrlResolution
    -0.65
     <=",
    -0.63
    long
    -0.58
    rungsseite
    -0.57
     longa
    -0.57
    Portale
    -0.56
    POSITIVE LOGITS
    resizingMask
    0.50
    an
    0.50
    AN
    0.46
    ret
    0.45
    테
    0.45
    re
    0.45
    anzi
    0.45
    ertos
    0.44
    saga
    0.44
     useDispatch
    0.44
    Activations Density 3.358%

    No Known Activations