© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8536
    Prev
    Next
    INDEX
    Explanations

    text related to terrorism, counter-terrorism, and radicalization.

    oai_token-act-pair · gemini-2.0-flash

    terms related to terrorism and extremist groups

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

    Islamic terrorist networks

    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
    JspWriter
    -0.77
     يتيمه
    -0.73
    FieldDescriptor
    -0.64
    
    -0.63
    脚注の使い方
    -0.63
    UnknownFieldSet
    -0.59
    databind
    -0.59
     dataSnapshot
    -0.58
     Chwiliwch
    -0.58
    XmlEnum
    -0.57
    POSITIVE LOGITS
     Islamic
    0.53
     NETWORK
    0.52
    cticide
    0.50
     networks
    0.48
     Islamist
    0.47
    network
    0.47
     network
    0.47
     ISIS
    0.47
     islamic
    0.46
    aspetto
    0.46
    Activations Density 2.001%

    No Known Activations