© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7522
    Prev
    Next
    INDEX
    Explanations

    snippets from a technical chatroom conversation, likely about computers

    oai_token-act-pair · gemini-2.0-flash

    Mixed French, English, code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     nahilalakip
    -1.07
    enumii
    -1.05
    httphttps
    -1.04
     disambiguazione
    -1.03
     تضيفلها
    -0.96
     utafitiHapana
    -0.96
    expandindo
    -0.93
    RenderAtEndOf
    -0.91
     autorytatywna
    -0.91
    didSet
    -0.90
    POSITIVE LOGITS
     (
    0.46
    ..
    0.43
    -
    0.43
     dis
    0.42
     least
    0.42
    dis
    0.42
    ...
    0.42
     de
    0.41
    …
    0.41
     b
    0.40
    Activations Density 1.438%

    No Known Activations