© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4258
    Prev
    Next
    INDEX
    Explanations

    language related to exposure to toxic substances.

    oai_token-act-pair · gemini-2.0-flash

    toxic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    LookAnd
    -0.85
     resourceCulture
    -0.60
    omitempty
    -0.59
     tweed
    -0.58
    abestanden
    -0.58
    iotensin
    -0.57
    RegistryLite
    -0.57
    parsedMessage
    -0.55
    ">//
    -0.54
     cocker
    -0.53
    POSITIVE LOGITS
     toxic
    1.22
     poison
    1.11
     Toxic
    1.05
     poisonous
    1.04
     chemical
    1.02
     toxins
    1.02
    Toxic
    1.00
     toxin
    0.98
    toxic
    0.98
     chemicals
    0.95
    Activations Density 2.236%

    No Known Activations