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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4599
    Prev
    Next
    INDEX
    Explanations

    language related to relationships and emotional turmoil

    oai_token-act-pair · gemini-2.0-flash

    marriage and relationships

    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
    gründet
    -0.51
     PublicKey
    -0.47
    ]>=
    -0.46
     @"/
    -0.46
     TestBed
    -0.45
     henvisninger
    -0.45
    choline
    -0.44
    Personensuche
    -0.43
    Composable
    -0.43
    équipement
    -0.43
    POSITIVE LOGITS
     engagements
    0.69
    Życiorys
    0.67
     engagement
    0.60
     Audiodateien
    0.59
     ENG
    0.55
     Dede
    0.55
    endpush
    0.55
     ddelweddau
    0.55
     depositphotos
    0.54
    IsContent
    0.52
    Activations Density 12.051%

    No Known Activations