© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 13992
    Prev
    Next
    INDEX
    Explanations

    sentences explaining political disagreements in American History

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     تضيفلها
    -0.93
     محفوظة
    -0.87
    UrlResolution
    -0.79
    
    -0.75
     للمعارف
    -0.71
     createSlice
    -0.67
    ptonshire
    -0.65
    StreetMap
    -0.65
    MENAFN
    -0.65
    iastes
    -0.63
    POSITIVE LOGITS
     disambiguazione
    0.52
    public
    0.50
    GENERIC
    0.47
    genti
    0.46
     público
    0.46
    urgence
    0.46
    >{@
    0.45
    Franco
    0.45
     kato
    0.45
     public
    0.45
    Activations Density 16.793%

    No Known Activations