© 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. 13352
    Prev
    Next
    INDEX
    Explanations

    code or log files.

    oai_token-act-pair · gemini-2.0-flash

    Code and logs

    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
    Rujukan
    -0.32
    expandindo
    -0.31
    hassee
    -0.31
    abestanden
    -0.31
    ContextHolder
    -0.31
     незавершена
    -0.31
     препратки
    -0.28
     Gerais
    -0.27
     baht
    -0.27
    ׁ
    -0.27
    POSITIVE LOGITS
    enterOuterAlt
    0.83
     كورة
    0.80
    doctype
    0.75
    ⋱
    0.75
    gäng
    0.75
    おきます
    0.74
    IsContent
    0.73
    enna
    0.72
    jectures
    0.72
     onAnimation
    0.71
    Activations Density 23.881%

    No Known Activations