© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11159
    Prev
    Next
    INDEX
    Explanations

    phrases related to physics experiments detecting and characterizing dark matter

    oai_token-act-pair · gemini-2.0-flash

    signature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    AndEndTag
    -0.81
     myſelf
    -0.81
    IndentedString
    -0.73
     raiſ
    -0.71
     Houſe
    -0.68
    MigrationBuilder
    -0.66
     itſelf
    -0.66
     houſe
    -0.65
     ExecuteAsync
    -0.65
     ―――――
    -0.65
    POSITIVE LOGITS
     us
    0.60
    SuppressLint
    0.47
     conditions
    0.46
     tr
    0.46
     
    0.45
    “
    0.45
    ustand
    0.44
     undangan
    0.44
    findpost
    0.43
     show
    0.43
    Activations Density 4.171%

    No Known Activations