© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15123
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of" and words connected to it, and also words like "state", "mis-", "his", "constitutional", and references.

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    InputTagHelper
    -0.86
    findpost
    -0.82
     kasarigan
    -0.71
     nakalista
    -0.69
    EndContext
    -0.69
    TagMode
    -0.65
    endphp
    -0.64
     onCreateView
    -0.63
    Abitanti
    -0.63
     CURIAM
    -0.62
    POSITIVE LOGITS
     linkovi
    0.54
     thier
    0.47
     dela
    0.45
     their
    0.44
     Their
    0.43
    Their
    0.40
     the
    0.39
     ſtate
    0.39
     eſt
    0.38
     Cæsar
    0.38
    Activations Density 13.817%

    No Known Activations