© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4513
    Prev
    Next
    INDEX
    Explanations

    capital letters, company names, or geographical places, in the context of seeking a job offer

    oai_token-act-pair · gemini-2.0-flash

    Tech companies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ře
    -0.51
     garrafa
    -0.51
     Hodge
    -0.48
     estúdio
    -0.46
     clairement
    -0.46
     sanitaires
    -0.45
    sätzlich
    -0.44
    latego
    -0.44
     soigneusement
    -0.44
     outpost
    -0.43
    POSITIVE LOGITS
     tech
    1.23
     Tech
    1.05
     Google
    1.04
     Silicon
    1.03
     companies
    1.02
     technology
    0.91
    Companies
    0.90
     Companies
    0.90
    Tech
    0.90
    Google
    0.90
    Activations Density 1.632%

    No Known Activations