© 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. 5977
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases including "to" or related to time/dates

    oai_token-act-pair · gemini-2.0-flash

    face-to-face interactions and dates

    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
    windowFixed
    -0.50
     kasarigan
    -0.41
     <<<<<<<<<<<<<<
    -0.41
     getItemId
    -0.40
     {}));
    -0.39
    ."));
    -0.38
    setVerticalGroup
    -0.38
     &,
    -0.38
     gynnwys
    -0.38
     })
    
    -0.37
    POSITIVE LOGITS
    bleau
    0.67
    cessite
    0.65
    quantum
    0.65
    secondary
    0.61
    aldas
    0.61
    hålla
    0.61
    føre
    0.60
    elevator
    0.60
     ويكيپيديا
    0.60
    cake
    0.60
    Activations Density 8.599%

    No Known Activations