© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1930
    Prev
    Next
    INDEX
    Explanations

    words starting with the syllable "cla" or ending with "ly."

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    MessageTagHelper
    -0.66
    ArrowToggle
    -0.60
    rungsseite
    -0.60
     MainAxisSize
    -0.58
    ral
    -0.54
    NUMX
    -0.54
    PerformLayout
    -0.54
    mapStateToProps
    -0.53
    دانشنامهٔ
    -0.50
    liness
    -0.50
    POSITIVE LOGITS
     MVP
    0.56
    vmware
    0.50
     MNRAS
    0.50
    MSD
    0.47
     voltmeter
    0.46
    isure
    0.45
    MVP
    0.45
     devenir
    0.45
    eper
    0.44
    epik
    0.43
    Activations Density 7.991%

    No Known Activations