© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9244
    Prev
    Next
    INDEX
    Explanations

    percentages and decimal numbers

    oai_token-act-pair · gemini-2.0-flash

    say "percent"

    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
     per
    -2.45
    per
    -1.80
     Per
    -1.76
    Per
    -1.73
     PER
    -1.41
    PER
    -1.31
    perma
    -0.91
    perse
    -0.81
    perg
    -0.80
    perin
    -0.80
    POSITIVE LOGITS
    Obrázky
    0.58
     Normdatei
    0.52
    MENAFN
    0.52
    
    0.49
    PreExecute
    0.48
    rolid
    0.46
     Commentaires
    0.45
     createSprite
    0.45
    ξε
    0.44
     cio
    0.43
    Activations Density 2.045%

    No Known Activations