© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4955
    Prev
    Next
    INDEX
    Explanations

    sentences where someone has the ability to do something and/or can in fact do something

    oai_token-act-pair · gemini-2.0-flash

    verbs related to ability and action

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    #+#
    -0.65
    DllImport
    -0.61
    Configurer
    -0.59
    stateProvider
    -0.58
    UObject
    -0.57
    علم
    -0.56
     wikipagina
    -0.56
     ISNI
    -0.55
    modelBuilder
    -0.55
    Identyfik
    -0.55
    POSITIVE LOGITS
     فريبيس
    0.50
     handled
    0.49
     handle
    0.48
     InputDecoration
    0.46
     navigate
    0.46
     understood
    0.46
    othed
    0.46
     interpret
    0.45
     analis
    0.44
    Припев
    0.44
    Activations Density 0.847%

    No Known Activations