© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3609
    Prev
    Next
    INDEX
    Explanations

    the names of cloud computing services and related jargon.

    oai_token-act-pair · gemini-2.0-flash

    Companies and services

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    SequentialGroup
    -1.00
    RenderAtEndOf
    -0.82
     ModelExpression
    -0.79
     Efq
    -0.77
     poffe
    -0.76
     jaws
    -0.76
    lapsingToolbar
    -0.75
    verwijspagina
    -0.75
     pleaſure
    -0.74
     Cæsar
    -0.74
    POSITIVE LOGITS
     principaux
    0.45
     sur
    0.42
    KE
    0.39
     sees
    0.39
    ATE
    0.38
     ostat
    0.38
    使
    0.38
    utnik
    0.38
    rungsseite
    0.38
    лог
    0.37
    Activations Density 2.638%

    No Known Activations