© 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. 9750
    Prev
    Next
    INDEX
    Explanations

    the phrase "how to"

    oai_token-act-pair · gemini-2.0-flash

    instances of the token 'to'

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

    to

    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
     moyen
    -0.52
     dared
    -0.48
    طريقة
    -0.47
    way
    -0.45
     gainera
    -0.45
     dares
    -0.45
    x
    -0.44
     tengah
    -0.44
     باخ
    -0.44
     متحده
    -0.42
    POSITIVE LOGITS
     estekak
    0.69
    Rhestr
    0.66
    .}(
    0.60
     mone
    0.60
    InjectAttribute
    0.59
    UnusedPrivate
    0.59
    CALCUL
    0.59
     mosaics
    0.57
     uſe
    0.57
    udadera
    0.57
    Activations Density 1.134%

    No Known Activations