© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12913
    Prev
    Next
    INDEX
    Explanations

    hyphens embedded within or at the end of words

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.57
     Reverso
    -0.49
    arXiv
    -0.44
    Passcode
    -0.42
    Portale
    -0.42
    wahati
    -0.41
     XCTest
    -0.41
     candidates
    -0.41
    avax
    -0.41
    æn
    -0.40
    POSITIVE LOGITS
     AssemblyProduct
    0.53
     sanitaires
    0.50
    DockStyle
    0.46
     démocr
    0.46
    XtraGrid
    0.45
     debout
    0.43
    IntoConstraints
    0.43
     nahilalakip
    0.42
    rrggbb
    0.42
     AssemblyCompany
    0.42
    Activations Density 0.750%

    No Known Activations