© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3507
    Prev
    Next
    INDEX
    Explanations

    words indicating potential threats and possible military actions

    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_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
    醐
    -0.59
     dotenv
    -0.58
    Билгалдахарш
    -0.57
     kiệm
    -0.54
     المعيارى
    -0.51
    Secure
    -0.49
     pylab
    -0.49
    zeptember
    -0.47
    expandindo
    -0.47
    rungsseite
    -0.46
    POSITIVE LOGITS
     للمعارف
    0.56
     rep
    0.54
     fight
    0.52
     років
    0.52
    ötä
    0.50
     Италијани
    0.49
     arm
    0.48
     suppress
    0.47
    merksam
    0.47
    iziert
    0.47
    Activations Density 3.580%

    No Known Activations