© 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. 101
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and superlatives

    oai_token-act-pair · gemini-2.0-flash

    Emphasizing descriptive words

    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
    !*\
    -0.68
    InstrumentedTest
    -0.57
     Signalez
    -0.52
    principalTable
    -0.52
     BIBSYS
    -0.50
     Sublime
    -0.49
    +#+
    -0.48
    WriteAttribute
    -0.48
    InvalidProtocol
    -0.48
    큼
    -0.47
    POSITIVE LOGITS
    Hard
    0.74
     hard
    0.73
     other
    0.71
    hard
    0.70
    ValueStyle
    0.69
     Hard
    0.67
    HARD
    0.66
     autres
    0.61
    MLLoader
    0.58
    Other
    0.54
    Activations Density 6.890%

    No Known Activations