© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9606
    Prev
    Next
    INDEX
    Explanations

    sentences containing "is", "are", or "was".

    oai_token-act-pair · gemini-2.0-flash

    legal terminology and court references

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

    is

    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
     part
    -0.56
     v
    -0.49
    المراجع
    -0.49
     kasarigan
    -0.48
    part
    -0.48
     Part
    -0.48
    verständlich
    -0.47
     ways
    -0.47
     a
    -0.45
    IContainer
    -0.45
    POSITIVE LOGITS
    UnusedPrivate
    0.99
     оригіналу
    0.75
    tanleria
    0.66
    LayoutStyle
    0.63
    webElementXpaths
    0.62
    RetentionPolicy
    0.60
     nakalista
    0.59
    ConstraintMaker
    0.58
    \{\\
    0.58
    WithIOException
    0.58
    Activations Density 1.126%

    No Known Activations