© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10002
    Prev
    Next
    INDEX
    Explanations

    terms of affirmation, such as "easy," "convenience," "now," "yes", "solution" or other things that confirm something

    oai_token-act-pair · gemini-2.0-flash

    Technical/business context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     sauvages
    -0.71
     avoient
    -0.71
     ainfi
    -0.66
     ciascuno
    -0.65
     dieux
    -0.65
     démocr
    -0.65
     Romains
    -0.64
     vocale
    -0.64
     rempliss
    -0.64
     automatiques
    -0.63
    POSITIVE LOGITS
    esModule
    0.71
    IBAction
    0.61
    AddHtmlAttribute
    0.59
     springfox
    0.58
    stdc
    0.56
    \{\\
    0.56
    istoitu
    0.55
    JNIEnv
    0.55
    +:+
    0.53
    NOPQRST
    0.52
    Activations Density 3.147%

    No Known Activations