© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2487
    Prev
    Next
    INDEX
    Explanations

    formal written communications from one entity to another, often in legal or business contexts.

    oai_token-act-pair · gemini-2.0-flash

    letter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     letter
    -2.70
    letter
    -2.42
    Letter
    -2.38
     letters
    -2.36
     Letter
    -2.33
     Letters
    -2.20
     LETTER
    -2.16
    letters
    -2.13
    Letters
    -2.03
     LETTERS
    -2.02
    POSITIVE LOGITS
    fjspx
    0.74
    GLOB
    0.51
     Bruch
    0.46
    tagPool
    0.46
    ercito
    0.45
     Wayback
    0.45
     Deel
    0.45
     FEED
    0.44
     Teig
    0.44
    erdo
    0.44
    Activations Density 10.697%

    No Known Activations