© 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. 12253
    Prev
    Next
    INDEX
    Explanations

    things related to doing ordinary activities and talking about those activities

    oai_token-act-pair · gemini-2.0-flash

    socializing

    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
    LookAnd
    -1.02
    
    -1.00
    DockStyle
    -0.93
    Parcelize
    -0.92
    Datuak
    -0.91
    ](#
    -0.89
     defaultstate
    -0.89
    parsedMessage
    -0.89
    StoryboardSegue
    -0.88
    AutoField
    -0.87
    POSITIVE LOGITS
    <bos>
    0.67
    D
    0.58
     filles
    0.49
    E
    0.47
    h
    0.47
    The
    0.47
    abol
    0.46
    '
    0.46
    H
    0.44
    Co
    0.43
    Activations Density 1.878%

    No Known Activations