© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13855
    Prev
    Next
    INDEX
    Explanations

    small numerical strings, especially those with brackets and less-than signs.

    oai_token-act-pair · gemini-2.0-flash

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    :✨
    -0.76
     الحره
    -0.74
     estekak
    -0.74
    henge
    -0.68
     henvisninger
    -0.68
     Signalez
    -0.68
    EDEFAULT
    -0.66
    standers
    -0.65
    ContentAlignment
    -0.65
    ScopeManager
    -0.64
    POSITIVE LOGITS
    <eos>
    0.45
     p
    0.43
    vägen
    0.42
    myapplication
    0.42
     human
    0.42
     vector
    0.42
    ilya
    0.42
     vorliegenden
    0.41
    tis
    0.41
    ēl
    0.41
    Activations Density 0.852%

    No Known Activations