© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12975
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to problems or identifying something

    oai_token-act-pair · gemini-2.0-flash

    forms of "is"

    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
    RectangleBorder
    -0.75
    mybatisplus
    -0.65
    RetentionPolicy
    -0.62
     ModelExpression
    -0.60
     تضيفلها
    -0.60
    transQ
    -0.59
    urcht
    -0.59
    BASELINE
    -0.59
     صوتيه
    -0.57
    rrggbb
    -0.56
    POSITIVE LOGITS
     is
    2.08
     είναι
    0.65
     be
    0.62
     है
    0.56
     está
    0.54
    Попис
    0.53
     است
    0.51
    ⓧ
    0.51
     هو
    0.49
    tande
    0.48
    Activations Density 0.948%

    No Known Activations