© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 14780
    Prev
    Next
    INDEX
    Explanations

    emotionally charged opinions and judgements

    oai_token-act-pair · gemini-2.0-flash

    Foreign language

    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
    umente
    -0.43
    rometers
    -0.42
    govine
    -0.40
    ANDUM
    -0.40
    hicles
    -0.40
     word
    -0.38
    __((
    -0.37
    hoga
    -0.37
    iba
    -0.37
    word
    -0.37
    POSITIVE LOGITS
     renseignements
    0.68
     ennemis
    0.66
     ſont
    0.66
     république
    0.66
     feroit
    0.65
    LookAnd
    0.65
     väg
    0.65
     âmes
    0.64
     émotions
    0.64
     étoient
    0.64
    Activations Density 5.574%

    No Known Activations