© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11193
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing judgment or evaluation, particularly regarding the likelihood or possibility of something.

    oai_token-act-pair · gemini-2.0-flash

    low probability or programs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    PreferredItem
    -0.65
     ContentValues
    -0.54
     Pläne
    -0.53
    획
    -0.52
     Planung
    -0.52
    Plans
    -0.51
    IntoConstraints
    -0.51
     InputDecoration
    -0.50
     plans
    -0.48
     diren
    -0.48
    POSITIVE LOGITS
    contentLoaded
    0.72
    matchCondition
    0.69
    >--}}
    0.68
     Seeder
    0.65
    /**
    0.64
     الحره
    0.60
     RemoteException
    0.58
    ')")
    0.58
    Activator
    0.56
     ujednoznacz
    0.56
    Activations Density 6.745%

    No Known Activations