© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2380
    Prev
    Next
    INDEX
    Explanations

    words related to marketing and sales

    oai_token-act-pair · gemini-2.0-flash

    technical/code language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -0.48
    RUnlock
    -0.46
     internazionali
    -0.46
     désigne
    -0.45
     Архивировано
    -0.44
     africains
    -0.44
     realizarse
    -0.43
     internationaux
    -0.43
     olduğunu
    -0.43
    amssymb
    -0.42
    POSITIVE LOGITS
    prefixer
    0.67
    mergeFrom
    0.63
    tagHelperRunner
    0.62
    WriteAttribute
    0.56
    GRANTED
    0.56
    IonicModule
    0.56
    Hozzáférés
    0.55
    oide
    0.54
    opy
    0.53
    addPreferredGap
    0.53
    Activations Density 1.120%

    No Known Activations