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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5918
    Prev
    Next
    INDEX
    Explanations

    the fragment "Hy" regardless of the surrounding characters

    oai_token-act-pair · gemini-2.0-flash

    hy

    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
     OFDb
    -0.50
    よいよ
    -0.47
     kasarigan
    -0.44
    ########.
    -0.43
    ^(@)
    -0.41
     eqn
    -0.41
     Southland
    -0.39
     chamber
    -0.39
    IndentedString
    -0.38
    截至
    -0.38
    POSITIVE LOGITS
    nities
    0.64
    XmlAccessorType
    0.63
    bridi
    0.63
    mergeFrom
    0.63
     onCancelled
    0.62
    intellij
    0.61
    toid
    0.60
    ICATED
    0.60
    ubility
    0.59
    WebServlet
    0.59
    Activations Density 4.052%

    No Known Activations