© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12021
    Prev
    Next
    INDEX
    Explanations

    "not" or negative terms, with some bonus for sports-related terms and "purpose".

    oai_token-act-pair · gemini-2.0-flash

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     not
    -1.38
    not
    -1.20
    Not
    -1.04
     Not
    -0.94
    NOT
    -0.89
     NOT
    -0.87
     niet
    -0.71
     nicht
    -0.66
     не
    -0.65
    <bos>
    -0.58
    POSITIVE LOGITS
    asteroide
    0.77
    IBOutlet
    0.75
     viewDidLoad
    0.69
    InvalidProtocol
    0.69
    expandindo
    0.68
     incomplète
    0.66
    ]^{-
    0.66
     المعيارى
    0.65
     createSprite
    0.65
    ustes
    0.64
    Activations Density 0.570%

    No Known Activations