© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10936
    Prev
    Next
    INDEX
    Explanations

    phrases that describe emotional connection or loss

    oai_token-act-pair · gemini-2.0-flash

    close

    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
    IsMutable
    -0.88
    ⓧ
    -0.73
     disambiguazione
    -0.70
    rrggbb
    -0.64
    ariConfig
    -0.59
     mergeFrom
    -0.57
     ujednoznacz
    -0.57
    Personendaten
    -0.56
    OGND
    -0.56
    orcid
    -0.55
    POSITIVE LOGITS
     close
    2.50
    close
    2.08
     Close
    2.02
     closest
    1.99
    Close
    1.92
     CLOSE
    1.88
     closer
    1.67
     near
    1.63
     nearest
    1.55
    CLOSE
    1.55
    Activations Density 0.836%

    No Known Activations