© 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. 3957
    Prev
    Next
    INDEX
    Explanations

    the word "active" and words used similarly to "active".

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "active"

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

    active

    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
     becauſe
    -0.69
    ſelves
    -0.68
     Jefus
    -0.67
     myſelf
    -0.66
     Efq
    -0.66
    ^(@)
    -0.66
     gyhoeddwyd
    -0.65
     poffible
    -0.64
     fubject
    -0.64
     normaux
    -0.63
    POSITIVE LOGITS
    tund
    0.50
    XmlAccessType
    0.49
     Mar
    0.48
     mar
    0.46
     فريبيس
    0.45
    EndProject
    0.45
    ommen
    0.44
     code
    0.44
    code
    0.44
     Boul
    0.44
    Activations Density 5.504%

    No Known Activations