© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14176
    Prev
    Next
    INDEX
    Explanations

    mentions of collections of artistic works, and the careers and accolades of artists producing those works.

    oai_token-act-pair · gemini-2.0-flash

    catalogue archive work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Obrázky
    -0.71
    balleur
    -0.59
    Ashlee
    -0.57
    κτηρισ
    -0.54
    NamedQuery
    -0.52
     Quora
    -0.50
     Administrativna
    -0.50
    ngdoc
    -0.49
     typhoid
    -0.49
    الحياه
    -0.47
    POSITIVE LOGITS
     ModelExpression
    0.69
     archives
    0.65
    ParallelGroup
    0.60
     AssemblyCulture
    0.58
     archive
    0.57
    ostar
    0.56
     Archive
    0.54
    ACEAE
    0.54
     hits
    0.54
     studio
    0.54
    Activations Density 2.250%

    No Known Activations