© 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. 13269
    Prev
    Next
    INDEX
    Explanations

    the word "cannot" or the contraction "can't"

    oai_token-act-pair · gemini-2.0-flash

    negations

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

    can't wait

    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
    ırl
    -0.52
    ny
    -0.46
     betweenstory
    -0.44
     Grunde
    -0.44
    quir
    -0.44
    Jäh
    -0.43
    였
    -0.43
     سبورت
    -0.42
    Aholisi
    -0.42
     vernac
    -0.42
    POSITIVE LOGITS
    ValueStyle
    0.86
     Anſ
    0.69
    SequentialGroup
    0.63
     useAppContext
    0.61
     AssemblyCulture
    0.60
    DockStyle
    0.59
    клопе
    0.56
     help
    0.56
     counter
    0.55
    AnchorStyles
    0.55
    Activations Density 0.320%

    No Known Activations