© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15890
    Prev
    Next
    INDEX
    Explanations

    pronouns and prepositions adjacent to words for targeting

    oai_token-act-pair · gemini-2.0-flash

    targeting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     recipient
    -1.30
     defendants
    -1.22
     defendant
    -1.21
     target
    -1.20
     recipients
    -1.20
     victim
    -1.17
     targets
    -1.16
     participant
    -1.13
     applicant
    -1.11
    victim
    -1.11
    POSITIVE LOGITS
    ніципа
    0.52
    SharedCtor
    0.44
     aggiorn
    0.43
    isalpha
    0.42
    IBar
    0.42
    meral
    0.42
    Heya
    0.41
     SDM
    0.41
    ésia
    0.40
    isfile
    0.40
    Activations Density 1.707%

    No Known Activations