© 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. 11779
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks, often in structured code

    oai_token-act-pair · gemini-2.0-flash

    parenthesis and quotes

    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
     poffible
    -0.66
     سكانية
    -0.66
    felves
    -0.61
     fufficient
    -0.59
     contextLoads
    -0.59
     considérons
    -0.58
     himſelf
    -0.57
    
    -0.57
     itſelf
    -0.56
    =$?
    -0.56
    POSITIVE LOGITS
     MyBatis
    0.66
    '):
    0.64
    ':
    0.63
    WriteLiteral
    0.58
    ’,
    0.58
    ActionButton
    0.56
    `,
    0.54
    ”),
    0.54
    '),
    0.54
     []:
    0.54
    Activations Density 8.414%

    No Known Activations