© 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. 4830
    Prev
    Next
    INDEX
    Explanations

    the words "read", "count" and "Description"

    oai_token-act-pair · gemini-2.0-flash

    Code/script snippets

    np_max-act · 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
    _
    -0.80
     تضيفلها
    -0.80
    __':
    -0.78
    }();
    -0.77
     betweenstory
    -0.76
    ("}");
    -0.74
    ₁)
    -0.74
    \"]
    -0.73
    ]**
    -0.73
    oa̍t
    -0.72
    POSITIVE LOGITS
    PickerController
    0.56
    tabular
    0.47
    d
    0.47
     muualla
    0.47
    t
    0.47
    omys
    0.47
     sooner
    0.46
    l
    0.45
    ()
    0.44
    vic
    0.43
    Activations Density 0.334%

    No Known Activations