© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4715
    Prev
    Next
    INDEX
    Explanations

    statistical measures and confidence intervals

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming concepts

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

    statistical significance

    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
     المعيارى
    -0.82
    хьтан
    -0.74
     صوتيه
    -0.67
    expandindo
    -0.65
     MainAxisSize
    -0.60
     BoxFit
    -0.60
    ovací
    -0.60
     فريبيس
    -0.59
    GHIJKLM
    -0.59
    tioners
    -0.57
    POSITIVE LOGITS
     handleMessage
    0.51
    styleUrls
    0.49
     Siddi
    0.45
    Equ
    0.45
    مصادر
    0.44
    twimg
    0.43
    paralle
    0.43
    íaco
    0.43
    XmlAccessorType
    0.43
     beards
    0.42
    Activations Density 7.791%

    No Known Activations