© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12965
    Prev
    Next
    INDEX
    Explanations

    phrases related to beginnings, becoming, and progress

    oai_token-act-pair · gemini-2.0-flash

    the token "to"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     growing
    -1.31
     developing
    -1.24
     emerging
    -1.23
    growing
    -1.21
    developing
    -1.13
     suddenly
    -1.09
     becoming
    -1.06
    becoming
    -1.05
    Growing
    -1.04
     rising
    -1.01
    POSITIVE LOGITS
     NgModule
    0.44
    Muon
    0.41
     Figs
    0.41
    حياتها
    0.40
     _$
    0.40
    FunctionFlags
    0.40
     doInBackground
    0.40
    estin
    0.40
    intestinal
    0.39
    commons
    0.39
    Activations Density 2.994%

    No Known Activations