© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9960
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to public welfare and societal well-being

    oai_token-act-pair · gemini-2.0-flash

    social, public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     eorum
    -0.43
     dramatique
    -0.43
     chỗ
    -0.43
    ayne
    -0.43
     nying
    -0.42
     Probate
    -0.42
     anonymously
    -0.41
    رایط
    -0.41
     valmist
    -0.40
    السلام
    -0.40
    POSITIVE LOGITS
    parsedMessage
    0.89
    contentLoaded
    0.84
    Sucesor
    0.84
     utafitiHapana
    0.82
    +:+
    0.76
     ModelExpression
    0.74
    MethodManager
    0.71
    ]")]
    0.71
    MENAFN
    0.70
    ])):
    0.70
    Activations Density 2.445%

    No Known Activations