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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10364
    Prev
    Next
    INDEX
    Explanations

    words from the Croatian language related to Facebook, SMS messages and phone numbers

    oai_token-act-pair · gemini-2.0-flash

    Code and mixed 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_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
     tartalomajánló
    -0.56
    kään
    -0.49
    layui
    -0.46
    SALT
    -0.45
    曖昧さ回避
    -0.43
    formKey
    -0.42
    ↩
    -0.42
     protoimpl
    -0.42
    imbawa
    -0.42
     phận
    -0.42
    POSITIVE LOGITS
    awtextra
    0.66
     nahilalakip
    0.65
    Obrázky
    0.61
    IBUS
    0.60
    glTexCoord
    0.59
    EDEFAULT
    0.58
    zędu
    0.57
    tima
    0.56
    ViewImports
    0.52
    RegressionTest
    0.52
    Activations Density 2.434%

    No Known Activations