© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7495
    Prev
    Next
    INDEX
    Explanations

    stative verbs

    oai_token-act-pair · gemini-2.0-flash

    achieving/accomplishing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    EndInit
    -0.66
    bukkit
    -0.63
     Préférences
    -0.55
     "..\..\
    -0.54
    MigrationBuilder
    -0.51
     Roskov
    -0.51
     initComponents
    -0.50
    mobileqq
    -0.50
    PerformLayout
    -0.49
    
    -0.49
    POSITIVE LOGITS
     accomplish
    0.84
     achieve
    0.82
     achieved
    0.81
     accomplished
    0.74
     achieves
    0.73
     achie
    0.69
     accomplishing
    0.65
    achieve
    0.65
     attainment
    0.64
     achieving
    0.63
    Activations Density 2.320%

    No Known Activations