© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4116
    Prev
    Next
    INDEX
    Explanations

    the word "flat"

    oai_token-act-pair · gemini-2.0-flash

    flat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ed
    -0.90
    er
    -0.76
    es
    -0.76
     
    -0.75
    M
    -0.72
     fact
    -0.71
    http
    -0.70
     the
    -0.68
     two
    -0.67
    de
    -0.67
    POSITIVE LOGITS
     Efq
    1.17
     Jefus
    1.07
    berdayakan
    1.02
     ainfi
    1.01
    ^(@)
    1.01
     houſe
    0.94
     Majefty
    0.93
     auroit
    0.91
     Wikiseite
    0.91
     NgModule
    0.90
    Activations Density 4.134%

    No Known Activations