© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14362
    Prev
    Next
    INDEX
    Explanations

    terms related to eye protection and vision correction.

    oai_token-act-pair · gemini-2.0-flash

    glasses and lenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     lens
    -1.23
     Lens
    -1.22
     glasses
    -1.17
    Lens
    -1.10
     Glasses
    -1.06
    glasses
    -1.05
     lenses
    -1.03
    lens
    -1.02
     Lenses
    -0.89
     eyeglasses
    -0.86
    POSITIVE LOGITS
    +#+
    0.85
     Waray
    0.68
     winds
    0.59
    GEBURTSDATUM
    0.59
    تقاوى
    0.58
    Wind
    0.56
     surla
    0.53
     wind
    0.52
     wraps
    0.52
    winds
    0.52
    Activations Density 1.701%

    No Known Activations