© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14835
    Prev
    Next
    INDEX
    Explanations

    verbs that describe a thing or state of being, or that connect a subject to a property or predicate

    oai_token-act-pair · gemini-2.0-flash

    instances of 'be' and related forms

    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
     myſelf
    -0.74
    IUrlHelper
    -0.65
     himſelf
    -0.63
     للمعارف
    -0.60
     itſelf
    -0.59
     Theſe
    -0.59
     Done
    -0.58
     iſt
    -0.58
     Efq
    -0.57
     themſelves
    -0.54
    POSITIVE LOGITS
     no
    0.66
    batore
    0.54
    no
    0.54
    OGND
    0.52
     BrowserModule
    0.51
    Jeografia
    0.51
     just
    0.49
    bayes
    0.46
    DatabaseError
    0.46
    المكان
    0.45
    Activations Density 2.105%

    No Known Activations