© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4423
    Prev
    Next
    INDEX
    Explanations

    text that gives instructions or safety warnings, especially those related to medications and hazardous materials

    oai_token-act-pair · gemini-2.0-flash

    technical terms or jargon

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

    technical words

    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
    CreateModel
    -0.77
     ujednoznacz
    -0.72
    rungsseite
    -0.67
    RenderAtEndOf
    -0.65
     disegno
    -0.60
     AttributeSet
    -0.58
    曖昧さ回避
    -0.58
     متعلقه
    -0.56
    Дереккөздер
    -0.56
    ValueStyle
    -0.54
    POSITIVE LOGITS
    apnews
    0.49
    plu
    0.48
    CURLOPT
    0.45
    ruptedException
    0.45
    apse
    0.45
     ex
    0.44
    ICTS
    0.43
     trans
    0.43
    PackageName
    0.43
     carte
    0.40
    Activations Density 1.053%

    No Known Activations