© 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. 11051
    Prev
    Next
    INDEX
    Explanations

    a mix of words relating to technical support, academic assignments, bureaucracy, sales and engineering.

    oai_token-act-pair · gemini-2.0-flash

    technology

    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
     GONNA
    -0.69
     Gonna
    -0.67
     gonna
    -0.60
    XtraBars
    -0.60
    Gonna
    -0.60
    gonna
    -0.60
    biggest
    -0.57
     gotta
    -0.56
    子里
    -0.55
     Wasn
    -0.53
    POSITIVE LOGITS
    findpost
    0.66
    ⓧ
    0.63
    stylers
    0.63
    parsedMessage
    0.62
     BoxDecoration
    0.61
     onCancelled
    0.59
     migrator
    0.58
    AndEndTag
    0.58
     postIndex
    0.58
    ępnie
    0.57
    Activations Density 0.139%

    No Known Activations