© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4395
    Prev
    Next
    INDEX
    Explanations

    titles of publications and authors, sometimes with surprising results

    oai_token-act-pair · gemini-2.0-flash

    academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     createSprite
    -0.63
     svolta
    -0.53
     intptr
    -0.51
    ochim
    -0.50
    hadur
    -0.50
     CanadaChoose
    -0.50
     pysty
    -0.49
    Marshal
    -0.49
     licha
    -0.49
     faptul
    -0.49
    POSITIVE LOGITS
    <bos>
    1.00
    tagHelperRunner
    0.65
     صوتيه
    0.56
     defaultstate
    0.54
    IContainer
    0.51
    Configurer
    0.51
     presentation
    0.50
     cuad
    0.50
     quæ
    0.50
    |}{}
    0.49
    Activations Density 1.483%

    No Known Activations