© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9321
    Prev
    Next
    INDEX
    Explanations

    phrases related to government or authority and phrases related to applying processes

    oai_token-act-pair · gemini-2.0-flash

    administration, management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     ſtand
    -0.58
    ecore
    -0.52
    makeConstraints
    -0.50
     reafon
    -0.49
    AndroidJUnit
    -0.49
     reaſon
    -0.49
     purpoſe
    -0.48
     spared
    -0.48
     atât
    -0.47
    NamedQuery
    -0.47
    POSITIVE LOGITS
    
    0.69
    شهاد
    0.65
     gynhyrchwyd
    0.64
    FormTagHelper
    0.63
    DebuggerStep
    0.63
    enumi
    0.61
    dega
    0.54
     amplify
    0.53
    LookAnd
    0.53
     InputDecoration
    0.52
    Activations Density 0.471%

    No Known Activations