© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14963
    Prev
    Next
    INDEX
    Explanations

    words that often begin a sentence offering a new piece of information or describing an overview, or words/phrases that indicate a summary or conclusion is being made.

    oai_token-act-pair · gemini-2.0-flash

    note

    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
    <bos>
    -0.81
    ModelAdmin
    -0.62
    DeleteBehavior
    -0.55
    ussis
    -0.52
     Batteries
    -0.51
     Ratings
    -0.51
     Bourgoin
    -0.50
     Baillargeon
    -0.50
     IPX
    -0.49
    ਭ
    -0.49
    POSITIVE LOGITS
    viewDid
    0.45
    ftance
    0.43
    viewWillAppear
    0.43
    stacle
    0.42
    ſtance
    0.41
     AnyObject
    0.41
     promosi
    0.40
    licet
    0.40
     때문
    0.39
    thető
    0.39
    Activations Density 2.557%

    No Known Activations