© 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. 6232
    Prev
    Next
    INDEX
    Explanations

    the word "take"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word 'take'

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

    take

    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
    SourceChecksum
    -0.62
    saraba
    -0.62
    numerusform
    -0.59
    maketitle
    -0.56
     Audiodateien
    -0.54
    FileDescriptor
    -0.54
    Kaieteur
    -0.54
    cetype
    -0.54
     purpoſe
    -0.54
    acles
    -0.54
    POSITIVE LOGITS
     iprot
    0.49
     part
    0.48
    part
    0.47
    nezeu
    0.45
    thalene
    0.44
    Part
    0.43
     legenda
    0.43
     leçons
    0.41
    habhar
    0.40
     Part
    0.40
    Activations Density 0.225%

    No Known Activations