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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4260
    Prev
    Next
    INDEX
    Explanations

    articles "a" and "an", especially when preceeding positive adjectives

    oai_token-act-pair · gemini-2.0-flash

    Positive reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    burg
    -0.48
    mal
    -0.47
    position
    -0.47
    is
    -0.47
    parti
    -0.46
     position
    -0.46
     e
    -0.46
    if
    -0.45
    bi
    -0.45
    ï
    -0.45
    POSITIVE LOGITS
    ScopeManager
    0.95
     Roskov
    0.84
    WebControls
    0.78
     rêver
    0.77
     Efq
    0.77
    ellido
    0.77
     Monfieur
    0.76
    StoreMessageInfo
    0.76
    PerformLayout
    0.74
    脚注の使い方
    0.74
    Activations Density 0.324%

    No Known Activations