Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10420
    Prev
    Next
    INDEX
    Explanations

    phrases like cutting-edge, leading-edge, forward-looking and ground-breaking that modify the word edge.

    oai_token-act-pair · gemini-2.0-flash

    Innovation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Roskov
    -0.60
    ContentAlignment
    -0.59
    Xna
    -0.58
    __*/
    -0.56
    GRANTED
    -0.56
    ReusableCell
    -0.55
    Datuak
    -0.55
    setVerticalGroup
    -0.54
     ModelExpression
    -0.54
    ftagPool
    -0.54
    POSITIVE LOGITS
     pioneering
    1.36
     groundbreaking
    1.33
     revolutionary
    1.30
     pioneer
    1.26
     ground
    1.20
     pione
    1.20
     innovative
    1.19
     cutting
    1.17
     pioneers
    1.16
     trail
    1.13
    Activations Density 1.497%

    No Known Activations