© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12129
    Prev
    Next
    INDEX
    Explanations

    snippets of code including years and package org lines

    oai_token-act-pair · gemini-2.0-flash

    ®

    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
    ViewImports
    -0.54
    stateProvider
    -0.53
    ugna
    -0.52
    ajuato
    -0.51
    IsPostBack
    -0.50
     motor
    -0.50
     viewType
    -0.49
     أمر
    -0.48
    InjectMocks
    -0.48
    haustible
    -0.48
    POSITIVE LOGITS
    principalColumn
    0.73
    Personendaten
    0.65
    تقاوى
    0.61
    Rüyada
    0.59
     мѣ
    0.56
     विश्वसनीयता
    0.55
    GEBURTS
    0.53
     distanciation
    0.52
     betweenstory
    0.52
    ///</
    0.52
    Activations Density 0.898%

    No Known Activations