© 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. 6372
    Prev
    Next
    INDEX
    Explanations

    descriptions of something becoming thin or thick

    oai_token-act-pair · gemini-2.0-flash

    thickness

    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
     thin
    -2.66
     Thin
    -2.59
    Thin
    -2.55
     thick
    -2.47
     Thick
    -2.38
     thicker
    -2.36
    Thick
    -2.30
     thinner
    -2.27
    thick
    -2.25
     thickness
    -2.19
    POSITIVE LOGITS
    ">//
    0.55
    RenderAtEndOf
    0.54
    Cryptography
    0.51
    HttpEntity
    0.47
    ologia
    0.45
    幕
    0.45
     electrolytic
    0.45
    ChildScrollView
    0.45
    lectricité
    0.45
    gunos
    0.45
    Activations Density 2.880%

    No Known Activations