© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14556
    Prev
    Next
    INDEX
    Explanations

    words related to medical treatments, mental conditions, and claims of mental impairment

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    phosa
    -0.60
    okovic
    -0.58
    oran
    -0.52
    featureID
    -0.51
     Nye
    -0.50
     osteoporosis
    -0.50
    XmlIgnore
    -0.49
     Galileo
    -0.46
    NOPQRST
    -0.46
     Intr
    -0.46
    POSITIVE LOGITS
     jadx
    0.56
     supplied
    0.53
    supplied
    0.51
     akad
    0.51
     Supplied
    0.48
     дописавши
    0.48
     Offered
    0.48
     PROVIDED
    0.48
    rolid
    0.48
    לך
    0.47
    Activations Density 5.232%

    No Known Activations