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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 2702
    Prev
    Next
    INDEX
    Explanations

    pronouns combined with auxiliary verbs and contractions.

    oai_token-act-pair · gemini-2.0-flash

    both

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ⓧ
    -0.66
    contentLoaded
    -0.65
    GEBURTSDATUM
    -0.60
     surla
    -0.56
     lenker
    -0.56
    MENAFN
    -0.54
    قایناق‌لار
    -0.52
     VIDEOTAPE
    -0.52
     Италијани
    -0.52
     ]];
    -0.51
    POSITIVE LOGITS
     both
    3.20
    both
    2.89
    Both
    2.67
     Both
    2.58
     BOTH
    2.20
    BOTH
    2.16
     entrambi
    1.98
    Ambos
    1.95
     Beide
    1.94
     begge
    1.92
    Activations Density 5.399%

    No Known Activations