© 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. 10329
    Prev
    Next
    INDEX
    Explanations

    a mix of Polish place names, a water reference, Russian characters, and a few German words related to verbs and sentence structure.

    oai_token-act-pair · gemini-2.0-flash

    Mixed content

    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
     которое
    -0.93
     яке
    -0.63
     оно
    -0.62
     Оно
    -0.62
     посвящен
    -0.60
     kterou
    -0.56
     которая
    -0.56
     která
    -0.56
     которую
    -0.56
     welches
    -0.55
    POSITIVE LOGITS
    MigrationBuilder
    0.70
    AndEndTag
    0.70
     relâche
    0.62
     Taktlose
    0.58
    Билгалдахарш
    0.58
     виправивши
    0.57
    ResumeLayout
    0.56
    Спасылкі
    0.55
    原始内容存档于
    0.54
     gynhyrchwyd
    0.54
    Activations Density 0.715%

    No Known Activations