© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3492
    Prev
    Next
    INDEX
    Explanations

    dates with months

    oai_token-act-pair · gemini-2.0-flash

    specific document formatting tags

    np_token-act-pair-logits · gpt-4o-mini

    capitalized/foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     NSCoder
    -0.80
    脚注の使い方
    -0.72
    ResumeLayout
    -0.63
    AccessFile
    -0.63
     дописавши
    -0.61
     MonoBehaviour
    -0.61
     tartalomajánló
    -0.60
    دانشنامهٔ
    -0.60
    MemoryWarning
    -0.59
     препратки
    -0.59
    POSITIVE LOGITS
    \
    0.53
    <h5>
    0.52
    <h4>
    0.51
     član
    0.51
     nors
    0.51
    praš
    0.50
     froid
    0.49
    <h3>
    0.48
    Values
    0.48
     fikir
    0.48
    Activations Density 0.296%

    No Known Activations