© 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. 6710
    Prev
    Next
    INDEX
    Explanations

    punctuation and other structural elements that delineate distinct sections of text

    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
    Nevertheless
    -0.95
     however
    -0.95
     Nevertheless
    -0.94
    Nonetheless
    -0.93
     Nonetheless
    -0.93
     even
    -0.92
     although
    -0.91
    even
    -0.91
    despite
    -0.90
    however
    -0.90
    POSITIVE LOGITS
     Majefty
    0.70
     Monfieur
    0.68
     myſelf
    0.68
     Theſe
    0.67
     Houſe
    0.66
     themſelves
    0.65
    ſelf
    0.65
     uſe
    0.63
     houſe
    0.62
     purpoſe
    0.62
    Activations Density 7.986%

    No Known Activations