© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10877
    Prev
    Next
    INDEX
    Explanations

    words that are verbs or related to changing things

    oai_token-act-pair · gemini-2.0-flash

    analysis and modification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     feroit
    -0.96
     ainfi
    -0.93
     Operate
    -0.86
     auroit
    -0.84
     mutate
    -0.84
     marry
    -0.82
     Diagnose
    -0.82
     pouvoit
    -0.82
     invade
    -0.81
     calibrate
    -0.81
    POSITIVE LOGITS
    WithIOException
    0.61
     nargin
    0.55
    velocityY
    0.53
     continúas
    0.52
    formatie
    0.49
     isempty
    0.48
     fte
    0.48
    iration
    0.48
     propTypes
    0.48
     getPassword
    0.47
    Activations Density 10.486%

    No Known Activations