© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11865
    Prev
    Next
    INDEX
    Explanations

    clauses with auxiliary verbs and words of possession

    oai_token-act-pair · gemini-2.0-flash

    have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    PerformLayout
    -0.52
    (['/
    -0.39
    SaveChangesAsync
    -0.39
     müsste
    -0.39
    False
    -0.37
    mal
    -0.37
    ype
    -0.36
    務省
    -0.35
     paš
    -0.35
    True
    -0.35
    POSITIVE LOGITS
    TagHelper
    0.76
     got
    0.72
    ItemBackground
    0.69
    opsida
    0.67
    ragalactic
    0.67
    RSpec
    0.66
    MemoryWarning
    0.66
    onActivityResult
    0.65
    NameInMap
    0.65
     estimés
    0.64
    Activations Density 1.817%

    No Known Activations