© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6166
    Prev
    Next
    INDEX
    Explanations

    alphanumeric strings that look like database keys and id numbers

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     C
    -2.17
    C
    -2.00
    c
    -1.95
     c
    -1.84
    setC
    -1.26
     getC
    -1.09
    Ｃ
    -1.05
    ｃ
    -0.86
    getC
    -0.75
    ᴄ
    -0.71
    POSITIVE LOGITS
     nahilalakip
    0.63
     snippetHide
    0.49
     ت
    0.43
    βά
    0.43
     []:
    0.42
     ویکی‌پدی
    0.42
    toire
    0.41
    weightedMode
    0.40
    iin
    0.40
    Datuak
    0.39
    Activations Density 2.773%

    No Known Activations