© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11842
    Prev
    Next
    INDEX
    Explanations

    content that is likely racially charged.

    oai_token-act-pair · gemini-2.0-flash

    attack

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ISupport
    -0.76
    
    -0.69
    SharedDtor
    -0.69
     متعلقه
    -0.66
    URLException
    -0.61
    databind
    -0.61
    ainville
    -0.61
     combineReducers
    -0.61
     مرئيه
    -0.60
    BagConstraints
    -0.60
    POSITIVE LOGITS
     attack
    1.43
     Attack
    1.34
     attacks
    1.32
    Attack
    1.27
     attacked
    1.27
    attack
    1.25
     Attacks
    1.20
     ATTACK
    1.20
     attacking
    1.20
    attacks
    1.10
    Activations Density 4.558%

    No Known Activations