© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15869
    Prev
    Next
    INDEX
    Explanations

    the letters "Al"

    oai_token-act-pair · gemini-2.0-flash

    Al

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ченное
    -0.48
    rolment
    -0.48
    Note
    -0.47
    Subview
    -0.47
     Note
    -0.44
    τία
    -0.43
    iley
    -0.41
    INCLUDING
    -0.41
    ilion
    -0.40
    ICEF
    -0.40
    POSITIVE LOGITS
     AttributeSet
    0.74
    Viitteet
    0.72
     réguli
    0.69
    (!__
    0.68
     חיצוניים
    0.65
     CURIAM
    0.63
    énario
    0.63
    verwijspagina
    0.62
     privées
    0.61
    tvguidetime
    0.61
    Activations Density 0.194%

    No Known Activations