© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2854
    Prev
    Next
    INDEX
    Explanations

    positive sentiment in descriptions of media, especially when it is receiving praise or attention

    oai_token-act-pair · gemini-2.0-flash

    positive feedback

    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
     Receiving
    -0.65
     receive
    -0.62
     Receive
    -0.60
     receiving
    -0.59
     received
    -0.57
    Receiving
    -0.55
    Receive
    -0.53
    received
    -0.53
     ricevere
    -0.51
     recib
    -0.51
    POSITIVE LOGITS
     disponibilités
    0.77
    ThroughAttribute
    0.72
    antMatchers
    0.68
     Blockly
    0.64
    UpInside
    0.64
    bootstrapcdn
    0.63
     initComponents
    0.63
    AndEndTag
    0.63
     '\\;'
    0.61
     UIFont
    0.60
    Activations Density 7.461%

    No Known Activations