© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11526
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to incidents such as assaults and crimes and legal procedures in courts

    oai_token-act-pair · gemini-2.0-flash

    words related to incidents of violence

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

    negative incidents

    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
     projects
    -0.45
     vz
    -0.44
     pulumi
    -0.43
     AttributeSet
    -0.43
    Tembelea
    -0.42
     Projects
    -0.41
     relationships
    -0.41
     ModelExpression
    -0.40
    nit
    -0.40
     khusus
    -0.40
    POSITIVE LOGITS
    fjspx
    0.72
     Мексичка
    0.72
     Varan
    0.66
     betweenstory
    0.66
    SequentialGroup
    0.62
    ViewFeatures
    0.60
    OrNil
    0.59
    ulemon
    0.59
     skirmish
    0.58
     attack
    0.58
    Activations Density 1.462%

    No Known Activations