© 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. 6444
    Prev
    Next
    INDEX
    Explanations

    named entities, especially organizations and people involved in business, politics, and entertainment.

    oai_token-act-pair · gemini-2.0-flash

    Acronyms or abbreviations

    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
    omitempty
    -0.49
    PerformLayout
    -0.49
     surla
    -0.47
     виправивши
    -0.47
    ResumeLayout
    -0.47
    SaveChangesAsync
    -0.47
    ViewChild
    -0.46
     مشين
    -0.45
    EndInit
    -0.45
    Попис
    -0.44
    POSITIVE LOGITS
     يتيمه
    0.64
    Berry
    0.56
    BURG
    0.50
     Bieber
    0.50
    ANDY
    0.50
     Berry
    0.49
    MIA
    0.49
     Murray
    0.48
    rians
    0.48
    Ming
    0.47
    Activations Density 12.433%

    No Known Activations