© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15273
    Prev
    Next
    INDEX
    Explanations

    random fragments of HTML and technical content

    oai_token-act-pair · gemini-2.0-flash

    Mac operating systems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Portale
    -0.54
    limus
    -0.51
     незавершена
    -0.50
    RenderAtEndOf
    -0.49
     Illness
    -0.48
     desp
    -0.47
     Krankheit
    -0.45
    GEBURTS
    -0.44
    apore
    -0.44
    chyma
    -0.44
    POSITIVE LOGITS
     useStyles
    0.60
     Galo
    0.56
    ParallelGroup
    0.54
     Lyd
    0.52
     useSelector
    0.51
     Alo
    0.50
    ($__
    0.50
    vVar
    0.50
    LookAnd
    0.49
    ArgsConstructor
    0.48
    Activations Density 1.055%

    No Known Activations