© 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. 10515
    Prev
    Next
    INDEX
    Explanations

    the word "true" and related words like "fact."

    oai_token-act-pair · gemini-2.0-flash

    true

    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
    msgTypes
    -0.61
     []:
    -0.56
    AlterField
    -0.54
    principalTable
    -0.54
     referenties
    -0.52
    astéro
    -0.52
     Discretion
    -0.52
    <bos>
    -0.52
    IBinder
    -0.51
    ])){
    -0.51
    POSITIVE LOGITS
     true
    0.72
     untrue
    0.63
     condition
    0.63
    condition
    0.60
    conditions
    0.58
     True
    0.57
     condições
    0.57
    Kondisi
    0.56
     conditions
    0.54
     TRUE
    0.54
    Activations Density 1.617%

    No Known Activations