© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6455
    Prev
    Next
    INDEX
    Explanations

    the word "the" or words ending in "ing" if they are followed or preceeded by location words

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     
    -0.48
    ,
    -0.48
     The
    -0.47
    ↵
    -0.47
    .
    -0.46
    -
    -0.45
     a
    -0.44
    ↵↵
    -0.43
    The
    -0.42
     and
    -0.41
    POSITIVE LOGITS
    Personendaten
    1.26
    MigrationBuilder
    1.20
     nahilalakip
    1.09
    AndEndTag
    1.05
     autorytatywna
    1.03
     nakalista
    0.97
    новниш
    0.96
    IntoConstraints
    0.96
     виправивши
    0.94
     surla
    0.93
    Activations Density 2.554%

    No Known Activations