© 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. 15311
    Prev
    Next
    INDEX
    Explanations

    technical terms related to biological and chemical processes

    oai_token-act-pair · gemini-2.0-flash

    induction

    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
    bashrc
    -0.55
    asgi
    -0.54
    RequiresApi
    -0.53
     TMPro
    -0.52
    ContentAsync
    -0.52
    LLocation
    -0.52
     переписи
    -0.51
     }</
    -0.51
    ("")]
    -0.49
    }{*}{
    -0.48
    POSITIVE LOGITS
    <bos>
    0.81
     disponibilités
    0.75
     ujednoznacz
    0.74
    Referencie
    0.69
    脚注の使い方
    0.61
     distanciation
    0.60
    AUTOR
    0.59
     assoluto
    0.59
     origines
    0.59
     ModelExpression
    0.58
    Activations Density 6.235%

    No Known Activations