© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12278
    Prev
    Next
    INDEX
    Explanations

    words of possession (pronouns, possessive nouns)

    oai_token-act-pair · gemini-2.0-flash

    Describing body parts

    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
     AssemblyTitle
    -0.88
    OGND
    -0.69
     TextAppearance
    -0.65
     gradova
    -0.57
     Roskov
    -0.56
    Tikang
    -0.55
     الاطلاع
    -0.52
    ylvan
    -0.51
    adhyay
    -0.50
    TintMode
    -0.50
    POSITIVE LOGITS
    原始内容存档于
    0.69
    存于互联网档案馆
    0.49
     harps
    0.48
    vogel
    0.48
    ContentAsync
    0.47
     spiders
    0.46
    imageshack
    0.46
     rejoindre
    0.45
    IDER
    0.45
     perma
    0.45
    Activations Density 11.743%

    No Known Activations