© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6851
    Prev
    Next
    INDEX
    Explanations

    references to conflict, fighting, and violence.

    oai_token-act-pair · gemini-2.0-flash

    Kill/defeat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     تانيه
    -0.68
     يتيمه
    -0.62
    ########.
    -0.57
     BoxDecoration
    -0.55
     Trident
    -0.54
    UnsafeEnabled
    -0.53
     trident
    -0.52
    PROLOG
    -0.52
     wireType
    -0.52
    tonsoft
    -0.52
    POSITIVE LOGITS
     kill
    1.25
     defeating
    1.14
     kills
    1.13
     killing
    1.10
    kill
    1.07
     against
    1.04
     defeat
    1.02
     KILL
    0.99
    Kill
    0.97
     defeated
    0.96
    Activations Density 1.227%

    No Known Activations