© 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. 10346
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to youth

    oai_token-act-pair · gemini-2.0-flash

    terms related to youth-friendly health services

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

    youth

    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
     }}"></
    -0.69
     ostavi
    -0.67
    SerializedName
    -0.67
     protoimpl
    -0.65
    EndProject
    -0.63
    Personendaten
    -0.61
    __*/
    -0.61
     ویکی‌پدی
    -0.60
    tagHelperRunner
    -0.60
    èdia
    -0.60
    POSITIVE LOGITS
    illigen
    0.52
     climá
    0.52
    ーション
    0.48
     Nicola
    0.47
    OutputType
    0.46
     effetto
    0.44
    ereum
    0.44
     carrera
    0.44
     Britton
    0.44
     đối
    0.43
    Activations Density 1.205%

    No Known Activations