© 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. 6734
    Prev
    Next
    INDEX
    Explanations

    personal experiences related to feelings and sensations as well as factual information and results from science experiments.

    oai_token-act-pair · gemini-2.0-flash

    Learned topics

    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
     MainAxisSize
    -0.60
    bodyParser
    -0.59
    ThroughAttribute
    -0.58
     Lightboxes
    -0.57
    aults
    -0.53
     مرئيه
    -0.52
    ærk
    -0.47
     betweenstory
    -0.47
    cipar
    -0.46
    jatel
    -0.46
    POSITIVE LOGITS
     sat
    0.77
    enumii
    0.60
    sat
    0.57
    VersionUID
    0.56
     learned
    0.55
     Sat
    0.55
     Learned
    0.55
    DebuggerStep
    0.54
    got
    0.54
    Sat
    0.52
    Activations Density 7.686%

    No Known Activations