© 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. 5689
    Prev
    Next
    INDEX
    Explanations

    instances of personal opinions or subjective statements and frequently includes qualifiers or hedges like "think", "probably", "can", "should", "would", "really", "may".

    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
     precisione
    -0.49
     températures
    -0.48
     fatica
    -0.47
    ..."
    -0.47
     goûts
    -0.46
     câbles
    -0.45
     SPANISH
    -0.43
     aveug
    -0.43
     ..."
    -0.43
     pitié
    -0.43
    POSITIVE LOGITS
    ISupport
    0.82
     LE
    0.65
     IM
    0.64
     MG
    0.63
     DE
    0.63
     LC
    0.63
     OC
    0.62
     EF
    0.62
     LF
    0.61
     BoxFit
    0.61
    Activations Density 21.877%

    No Known Activations