© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6699
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize importance or belonging

    oai_token-act-pair · gemini-2.0-flash

    strength

    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
    vantages
    -0.74
    országban
    -0.72
    DockStyle
    -0.71
    IsPostBack
    -0.70
    ]--;
    -0.69
    bcryptjs
    -0.68
     дописавши
    -0.68
    XmlAccessType
    -0.68
    phazard
    -0.68
    jsonwebtoken
    -0.66
    POSITIVE LOGITS
     strength
    0.62
     strong
    0.56
    Hochspringen
    0.54
    strength
    0.48
     Strength
    0.47
     Strong
    0.46
     STRENGTH
    0.44
     fuertes
    0.43
     STRONG
    0.43
     stronger
    0.42
    Activations Density 2.158%

    No Known Activations