© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1529
    Prev
    Next
    INDEX
    Explanations

    place names

    oai_token-act-pair · gemini-2.0-flash

    legal and geographical locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    دانشنامهٔ
    -0.83
     мәкалә
    -0.82
     esternos
    -0.79
     AppCompatTheme
    -0.77
     Marathon
    -0.70
     actionMode
    -0.69
    apunov
    -0.69
     للاسماء
    -0.69
     lamella
    -0.68
     RAILROAD
    -0.68
    POSITIVE LOGITS
    protoc
    0.45
     Google
    0.44
    VIAF
    0.41
    ljeno
    0.40
    CURLOPT
    0.40
    SuppressLint
    0.40
     NSW
    0.40
    Connecticut
    0.40
    Tul
    0.40
     google
    0.39
    Activations Density 4.189%

    No Known Activations