© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7853
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "When" or "In" that mention time passing, cause/effect relationships, or conditions.

    oai_token-act-pair · gemini-2.0-flash

    when

    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
    })));
    -0.77
    findpost
    -0.60
    They
    -0.59
    ----</
    -0.59
     They
    -0.59
    )");
    
    -0.59
    tvguidetime
    -0.57
    }))
    
    -0.57
     of
    -0.57
     חיצוניים
    -0.57
    POSITIVE LOGITS
     contemporaine
    0.59
     sanitarias
    0.54
     touristique
    0.52
     sposa
    0.51
    час
    0.49
    IBAction
    0.49
     tartalomajánló
    0.48
     médicale
    0.48
    lıyor
    0.48
     vanished
    0.48
    Activations Density 11.456%

    No Known Activations