© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15460
    Prev
    Next
    INDEX
    Explanations

    contexts in which something is being analyzed, rated, or evaluated

    oai_token-act-pair · gemini-2.0-flash

    relationships between items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     AssemblyCulture
    -0.73
    brido
    -0.62
    ResumeLayout
    -0.59
    mapreduce
    -0.59
    DllImport
    -0.59
    TestTools
    -0.55
    Bioaccumulative
    -0.55
    olidated
    -0.54
     Uff
    -0.52
     Clearance
    -0.51
    POSITIVE LOGITS
     ModelExpression
    0.65
     صوتيه
    0.60
     Приступљено
    0.59
     تانيه
    0.59
    StoryboardSegue
    0.59
    %)$
    0.56
    >();
    0.53
    <bos>
    0.52
     protoimpl
    0.50
    __':
    0.47
    Activations Density 1.796%

    No Known Activations