© 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. 10107
    Prev
    Next
    INDEX
    Explanations

    the word "force" or Italian text related to the University of Pisa

    oai_token-act-pair · gemini-2.0-flash

    Academic/physics papers

    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
     $_"
    -1.38
     Houſe
    -1.30
     photolibrary
    -1.28
     Majefty
    -1.27
    ^(@)
    -1.22
     ―――――
    -1.21
     Anſ
    -1.20
     CreateTagHelper
    -1.20
     purpoſe
    -1.20
     fevere
    -1.19
    POSITIVE LOGITS
     the
    1.33
     a
    1.05
    <bos>
    1.02
    ↵↵
    1.01
    ↵
    0.94
     The
    0.94
     I
    0.91
     in
    0.90
     and
    0.90
     that
    0.89
    Activations Density 0.071%

    No Known Activations