© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14363
    Prev
    Next
    INDEX
    Explanations

    the word "square"

    oai_token-act-pair · gemini-2.0-flash

    square

    np_max-act · gemini-2.0-flash

    square

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     itſelf
    -1.68
     myſelf
    -1.59
     Efq
    -1.37
     Jefus
    -1.37
     raiſ
    -1.35
     pleaſure
    -1.29
     Monfieur
    -1.26
     ་་
    -1.24
    ſelf
    -1.24
    InputBorder
    -1.23
    POSITIVE LOGITS
     the
    0.82
     his
    0.68
     a
    0.63
     but
    0.62
    y
    0.59
     confirmer
    0.57
    s
    0.56
     their
    0.56
     its
    0.55
     from
    0.55
    Activations Density 1.990%

    No Known Activations