© 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. 12479
    Prev
    Next
    INDEX
    Explanations

    words related to design and construction

    oai_token-act-pair · gemini-2.0-flash

    shapes and movement

    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
     stamens
    -0.74
    BindingResult
    -0.69
    DialogInterface
    -0.68
    PreExecute
    -0.68
    OGND
    -0.65
     calyx
    -0.64
    ToAction
    -0.63
    loem
    -0.63
    Swal
    -0.62
     onPostExecute
    -0.61
    POSITIVE LOGITS
     것이다
    0.51
    órico
    0.47
     moving
    0.46
    toBeDefined
    0.46
    sibile
    0.45
    ۇ
    0.45
     sonhos
    0.45
     lục
    0.44
    óricas
    0.44
    افية
    0.44
    Activations Density 2.080%

    No Known Activations