© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11108
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs like "be", "are", and "able".

    oai_token-act-pair · gemini-2.0-flash

    Able

    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
    Ability
    -0.75
     Been
    -0.70
     Ability
    -0.70
     capability
    -0.70
     capaz
    -0.66
     capable
    -0.64
     capacidade
    -0.64
     Capability
    -0.63
    capability
    -0.62
     ability
    -0.59
    POSITIVE LOGITS
    enumi
    0.69
    UnusedPrivate
    0.69
    PerformLayout
    0.67
    DockStyle
    0.66
     resourceCulture
    0.66
    journ
    0.57
     Catawiki
    0.56
    Nightmare
    0.56
     SqlCommand
    0.54
    RefNanny
    0.53
    Activations Density 5.587%

    No Known Activations