© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6244
    Prev
    Next
    INDEX
    Explanations

    the adjective "big" or similar adjectives that mean the same thing

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word 'big'

    np_token-act-pair-logits · gpt-4o-mini

    big

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    //}
    -0.64
    ymce
    -0.61
     Wikimedijinoj
    -0.59
    الحياه
    -0.55
    neté
    -0.54
    országban
    -0.52
    ंदीखरीदारी
    -0.52
     föruts
    -0.51
     StringTokenizer
    -0.51
     bakgrund
    -0.51
    POSITIVE LOGITS
    tagHelperRunner
    0.59
    AutoScale
    0.56
    +:+
    0.54
    OSH
    0.52
     HOLE
    0.52
     hole
    0.50
    getWriter
    0.49
     name
    0.47
     bat
    0.46
     ole
    0.46
    Activations Density 1.503%

    No Known Activations