© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6409
    Prev
    Next
    INDEX
    Explanations

    words related to battles with heroes trying to stop villains

    oai_token-act-pair · gemini-2.0-flash

    stop

    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
     kämpfen
    -0.65
     bekämp
    -0.63
     menac
    -0.63
    resistance
    -0.63
     attacking
    -0.60
    ^(@)
    -0.60
    Resistant
    -0.59
     feind
    -0.59
     Protecting
    -0.57
     luchando
    -0.57
    POSITIVE LOGITS
     stop
    1.30
     stopped
    1.23
     stops
    1.16
     stopping
    1.13
     Stop
    1.05
    stop
    1.05
     STOP
    1.03
    Stop
    1.00
    STOP
    0.93
     Stopped
    0.93
    Activations Density 3.544%

    No Known Activations