© 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. 15295
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "provided" and the preposition "to", and email or social media symbols like "@".

    oai_token-act-pair · gemini-2.0-flash

    @

    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
    f
    -1.70
    if
    -1.62
    p
    -1.59
    to
    -1.59
    i
    -1.56
    in
    -1.56
    n
    -1.55
    1
    -1.55
    2
    -1.54
    for
    -1.52
    POSITIVE LOGITS
    ratulations
    1.98
    iffance
    1.88
    — 
    1.88
    bibfield
    1.84
    BibitemShut
    1.83
    NUMX
    1.79
    %\]
    1.77
    polation
    1.77
    CHREIB
    1.75
    ]='\
    1.75
    Activations Density 3.151%

    No Known Activations