© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13028
    Prev
    Next
    INDEX
    Explanations

    reports of death or injury by shooting or animal attack

    oai_token-act-pair · gemini-2.0-flash

    Acts of violence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    encodeWith
    -0.66
    ziell
    -0.62
     initComponents
    -0.60
     leia
    -0.57
    afficheront
    -0.56
    Litteratur
    -0.54
     htmlFor
    -0.53
    AndEndTag
    -0.53
    Cord
    -0.52
    iastes
    -0.52
    POSITIVE LOGITS
    odeficiency
    0.48
    سطس
    0.47
    السكان
    0.45
     distancias
    0.44
    Ivoire
    0.44
    ⓧ
    0.44
     reaper
    0.43
     متعلقه
    0.43
    блица
    0.42
    UnsafeEnabled
    0.42
    Activations Density 2.099%

    No Known Activations