© 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. 11701
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to data reconstruction, especially in the context of imaging

    oai_token-act-pair · gemini-2.0-flash

    mathematical/data analysis operations

    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
     الحره
    -0.70
    ResumeLayout
    -0.59
    PINES
    -0.54
    reness
    -0.54
    żenie
    -0.49
    antMatchers
    -0.49
     credence
    -0.49
     Weid
    -0.47
    olfen
    -0.47
    anso
    -0.47
    POSITIVE LOGITS
    SceneManagement
    0.65
    AndEndTag
    0.57
    StoryboardSegue
    0.54
    HasForeignKey
    0.54
    henswürdigkeiten
    0.53
    цездатний
    0.53
    спонд
    0.52
     PeEnEo
    0.51
     BrowserModule
    0.50
    ModelAdmin
    0.49
    Activations Density 9.167%

    No Known Activations