© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14016
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating a casual conversation or a question / answering exchange.

    oai_token-act-pair · gemini-2.0-flash

    conversational interjections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    はじめに
    -0.57
     in
    -0.55
     by
    -0.54
    fromCharCode
    -0.54
     as
    -0.52
    __).
    -0.51
     since
    -0.51
    sprogramm
    -0.50
    <bos>
    -0.49
     оригіналу
    -0.49
    POSITIVE LOGITS
     fhew
    0.68
     deſt
    0.62
     Baillargeon
    0.61
    RegressionTest
    0.60
     ſta
    0.58
     anſ
    0.58
     tranſ
    0.57
     ſind
    0.57
     quæ
    0.56
    UserScript
    0.56
    Activations Density 12.898%

    No Known Activations