© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9612
    Prev
    Next
    INDEX
    Explanations

    words ending in "ing", "read", name abbreviations, or the letters "inner", "arky", "umb", or "allow"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ainfi
    -1.09
    <bos>
    -1.05
     avoient
    -0.98
     feroit
    -0.96
     plufieurs
    -0.94
     pouvoit
    -0.94
     Efq
    -0.92
     auroit
    -0.92
     Monfieur
    -0.92
    __':
    -0.91
    POSITIVE LOGITS
    ...
    0.62
    </b>
    0.52
    O
    0.50
    les
    0.49
    t
    0.47
    iche
    0.47
    0
    0.47
    Il
    0.47
    ering
    0.46
    <b>
    0.45
    Activations Density 0.728%

    No Known Activations