© 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. 14
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or symbols that separate content, as well as some song details

    oai_token-act-pair · 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
     song
    -0.91
    ArrowToggle
    -0.76
     music
    -0.76
    ⓧ
    -0.70
    BeginContext
    -0.68
    WebVitals
    -0.67
     musical
    -0.66
     soundtrack
    -0.65
    song
    -0.64
    WriteTagHelper
    -0.63
    POSITIVE LOGITS
     Dude
    0.51
    はじめに
    0.51
     aprovecha
    0.49
     kwanza
    0.47
    󠁴
    0.47
     Regie
    0.46
    yski
    0.46
    uerst
    0.45
     direitos
    0.44
    Dude
    0.44
    Activations Density 13.045%

    No Known Activations