© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14481
    Prev
    Next
    INDEX
    Explanations

    text referring to politics and international conflict.

    oai_token-act-pair · gemini-2.0-flash

    US foreign policy

    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
    Personendaten
    -0.74
     bonté
    -0.62
    ificato
    -0.61
     defaultstate
    -0.60
     <<<<<<<<<<<<<<
    -0.60
     greateſt
    -0.59
     beginnetje
    -0.58
    RuleContext
    -0.57
     Chaldean
    -0.57
     Chasse
    -0.56
    POSITIVE LOGITS
     transfieras
    0.50
    usermodel
    0.49
    AsyncResult
    0.48
     betweenstory
    0.46
    Predic
    0.45
     al
    0.44
     [*]
    0.43
    ORPG
    0.43
    vajal
    0.42
    regular
    0.40
    Activations Density 2.943%

    No Known Activations