© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12432
    Prev
    Next
    INDEX
    Explanations

    studies in which results are being evaluated, particularly where there is a lack of knowledge or something is unexplored

    oai_token-act-pair · gemini-2.0-flash

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     vitt
    -0.59
     Pacífico
    -0.58
     venons
    -0.52
     auguri
    -0.49
     republics
    -0.49
     Equatorial
    -0.48
    fsp
    -0.48
     mijne
    -0.46
     Borel
    -0.45
     ſte
    -0.45
    POSITIVE LOGITS
    MessageTagHelper
    0.66
    AnchorTagHelper
    0.59
    σιμοποι
    0.58
    principalColumn
    0.56
    abilia
    0.54
      (
    0.54
    ----</
    0.50
    verwijspagina
    0.50
    MessageOf
    0.50
    ']],
    0.49
    Activations Density 0.770%

    No Known Activations