© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7680
    Prev
    Next
    INDEX
    Explanations

    verbs with endings like -ing, -ed, or which indicate an impact or change

    oai_token-act-pair · gemini-2.0-flash

    factor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     disambiguazione
    -0.89
    homonymie
    -0.74
    Bronnen
    -0.62
    +:+
    -0.62
    URLException
    -0.59
     Administrativna
    -0.58
    
    -0.54
    SuppressMessage
    -0.53
     mapStateToProps
    -0.52
     Lightboxes
    -0.52
    POSITIVE LOGITS
     factor
    0.67
     factors
    0.62
     effect
    0.59
    factor
    0.56
     Factors
    0.54
     force
    0.54
    짓
    0.54
     Faktoren
    0.53
    force
    0.52
    factors
    0.52
    Activations Density 1.619%

    No Known Activations