© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3466
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and present participle verbs describing violent actions or strong emotion

    oai_token-act-pair · gemini-2.0-flash

    screaming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     تانيه
    -0.82
     greateſt
    -0.69
    jsxFileName
    -0.68
    исленность
    -0.68
     ſtate
    -0.67
     '\\;'
    -0.64
     passada
    -0.63
     ſtre
    -0.63
    GraphicsUnit
    -0.62
    DotNetBar
    -0.61
    POSITIVE LOGITS
     Inf
    0.48
    iettes
    0.47
     Ton
    0.45
    ifflin
    0.45
     ujednoznacz
    0.45
    eria
    0.45
    icator
    0.44
     dile
    0.43
     Je
    0.42
    tack
    0.42
    Activations Density 6.825%

    No Known Activations