© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13531
    Prev
    Next
    INDEX
    Explanations

    the letter B followed by or preceded by another letter

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     chromat
    -0.44
    ENODEV
    -0.43
     CommonModule
    -0.41
    rogels
    -0.40
    Pfalz
    -0.38
    bootstrapcdn
    -0.38
    fetchone
    -0.38
     sap
    -0.37
     sha
    -0.37
    cault
    -0.37
    POSITIVE LOGITS
     оригіналу
    0.75
     nahilalakip
    0.72
     mourut
    0.67
    ThroughAttribute
    0.65
     հղումներ
    0.64
     tartalomajánló
    0.62
    出版年
    0.60
    췄
    0.59
     nationales
    0.59
     समीक्षाओं
    0.59
    Activations Density 0.496%

    No Known Activations