© 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. 11005
    Prev
    Next
    INDEX
    Explanations

    descriptions of furniture, especially reclining chairs and nightstands

    oai_token-act-pair · gemini-2.0-flash

    stand

    np_max-act · gemini-2.0-flash

    stand

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     GenerationType
    -0.62
    ManyToMany
    -0.56
    mishes
    -0.54
     Egli
    -0.52
    OutputType
    -0.50
     للمعارف
    -0.48
    hésite
    -0.48
     Ensuring
    -0.48
     revés
    -0.47
     Bew
    -0.47
    POSITIVE LOGITS
     Wicidata
    0.56
    addContainerGap
    0.52
     doInBackground
    0.50
    Xna
    0.50
    Autoritní
    0.49
    PerformLayout
    0.48
     تكبرها
    0.48
    EndInit
    0.48
     snippetHide
    0.47
     ***!
    0.47
    Activations Density 0.163%

    No Known Activations