© 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. 14568
    Prev
    Next
    INDEX
    Explanations

    uses of "which" and other relative pronouns.

    oai_token-act-pair · gemini-2.0-flash

    relative pronouns and auxiliary verbs

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

    which

    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
    noinspection
    -0.83
    󠁧
    -0.72
    RepeatedField
    -0.70
     EdgeInsets
    -0.67
    NewUrlParser
    -0.66
    LOAT
    -0.65
    enumii
    -0.65
     الدولى
    -0.64
    zzleHttp
    -0.64
    ագրություններ
    -0.62
    POSITIVE LOGITS
     we
    0.72
     is
    0.72
     they
    0.69
     means
    0.67
     contains
    0.65
     hasn
    0.62
     was
    0.61
    ,
    0.61
     doesn
    0.61
     you
    0.60
    Activations Density 3.728%

    No Known Activations