© 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. 12924
    Prev
    Next
    INDEX
    Explanations

    repeated letters or strings of letters that indicate excitement or exasperation

    oai_token-act-pair · gemini-2.0-flash

    Repeated characters

    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
    
    -0.84
    PerformLayout
    -0.78
    PhysRevD
    -0.73
    IntoConstraints
    -0.73
    Vidite
    -0.71
     autorytatywna
    -0.69
    principalColumn
    -0.63
    AddHtmlAttribute
    -0.63
    PMailer
    -0.62
    consulté
    -0.62
    POSITIVE LOGITS
    出版年
    0.58
     NgModule
    0.51
     desaparecer
    0.44
     arrives
    0.42
    ikkert
    0.40
     zato
    0.40
     ESF
    0.40
    립
    0.40
    auto
    0.39
     xs
    0.39
    Activations Density 0.321%

    No Known Activations