© 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. 3086
    Prev
    Next
    INDEX
    Explanations

    comparisons using the words "rather", "than", "is", "what", "the", "or", and "if".

    oai_token-act-pair · gemini-2.0-flash

    technical terms or jargon

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

    Disagreement/refutation

    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
     للمعارف
    -0.74
     EconPapers
    -0.70
    脚注の使い方
    -0.66
     Administrativna
    -0.66
    JspWriter
    -0.63
    __);
    -0.60
    parsedMessage
    -0.59
    ArrowToggle
    -0.59
    AndEndTag
    -0.59
     nakalista
    -0.58
    POSITIVE LOGITS
     Admit
    0.48
     total
    0.47
     a
    0.46
     unsub
    0.46
     tuyển
    0.45
    otal
    0.44
     verwijzen
    0.44
    nical
    0.43
     jambe
    0.43
     klikken
    0.42
    Activations Density 2.861%

    No Known Activations