© 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. 8387
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially C/C++ and Javascript including angle-brackets, or code in other languages containing the letter "F"

    oai_token-act-pair · gemini-2.0-flash

    Code and file paths

    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
    __*/
    -0.82
    
    -0.81
    Hauptartikel
    -0.81
     OFDb
    -0.76
    ########.
    -0.75
    oa̍t
    -0.75
    ThroughAttribute
    -0.75
     تضيفلها
    -0.74
    AnimationsModule
    -0.74
    PerformLayout
    -0.71
    POSITIVE LOGITS
    ôle
    0.45
     blz
    0.44
    poca
    0.44
     dene
    0.42
    irmed
    0.41
    outed
    0.41
     cæ
    0.41
    azia
    0.40
    ail
    0.40
    lashed
    0.40
    Activations Density 23.368%

    No Known Activations