© 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. 7878
    Prev
    Next
    INDEX
    Explanations

    single characters, code and math symbols

    oai_token-act-pair · gemini-2.0-flash

    say "= "

    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
     =
    -1.65
     $=$
    -1.02
    SceneManagement
    -0.93
    setVerticalGroup
    -0.92
    >=</
    -0.88
    =
    -0.87
    IntoConstraints
    -0.82
     $=
    -0.78
    RetentionPolicy
    -0.76
     $=\
    -0.75
    POSITIVE LOGITS
     loan
    1.13
    Borrow
    1.07
    Loan
    1.07
     borrow
    1.06
    loan
    1.00
     Loan
    1.00
    borrow
    1.00
     borrower
    0.99
     borrowers
    0.98
     loans
    0.97
    Activations Density 3.557%

    No Known Activations