© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9071
    Prev
    Next
    INDEX
    Explanations

    technical writing words

    oai_token-act-pair · gemini-2.0-flash

    terms related to heavy machinery

    np_token-act-pair-logits · gpt-4o-mini

    Excavation equipment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     TextAppearance
    -0.75
     transférez
    -0.69
    CppMethod
    -0.66
    Przypisy
    -0.65
     ExecuteAsync
    -0.60
    nextProps
    -0.57
    KURZBESCHREIBUNG
    -0.53
     mukana
    -0.52
    astify
    -0.52
    STO
    -0.52
    POSITIVE LOGITS
     rock
    0.53
     earth
    0.51
    Cater
    0.50
     comp
    0.50
    ément
    0.50
    avyzd
    0.49
    \{\\
    0.49
     tracked
    0.48
     excavator
    0.48
     الدولى
    0.48
    Activations Density 2.446%

    No Known Activations