© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16254
    Prev
    Next
    INDEX
    Explanations

    the words "else", "deal" or "spirit," potentially in the context of interpersonal interactions

    oai_token-act-pair · gemini-2.0-flash

    else

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ratulations
    -1.55
    æus
    -1.41
    polation
    -1.40
    ousand
    -1.37
    ]='\
    -1.35
    gnition
    -1.35
    uesday
    -1.35
    CHREIB
    -1.30
    ENEFITS
    -1.30
    uests
    -1.30
    POSITIVE LOGITS
    I
    1.07
    A
    1.05
    B
    0.99
    R
    0.96
    (
    0.96
    a
    0.96
    H
    0.95
    if
    0.93
    h
    0.92
    P
    0.91
    Activations Density 2.035%

    No Known Activations