© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12233
    Prev
    Next
    INDEX
    Explanations

    phrases including the word "same" that describe a relation between different things

    oai_token-act-pair · gemini-2.0-flash

    same people reasons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     myſelf
    -0.62
    équences
    -0.57
    SBATCH
    -0.54
     ModelAndView
    -0.54
     Theſe
    -0.53
    rances
    -0.51
     الرخصة
    -0.51
    HostException
    -0.51
    PointerException
    -0.50
     TextInputType
    -0.50
    POSITIVE LOGITS
    InjectAttribute
    0.63
    enumi
    0.58
    ńczy
    0.57
    saraba
    0.57
    Same
    0.56
     same
    0.56
    same
    0.55
     bire
    0.55
     <<<<<<<<<<<<<<
    0.53
    twimg
    0.51
    Activations Density 1.540%

    No Known Activations