© 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. 4030
    Prev
    Next
    INDEX
    Explanations

    words related to mission statements and personal development used in career environments

    oai_token-act-pair · gemini-2.0-flash

    team

    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
    <bos>
    -0.93
    Pretty
    -0.40
    Interestingly
    -0.39
     apparently
    -0.39
     offenbar
    -0.38
     Tetapi
    -0.37
    通し
    -0.37
    t
    -0.36
    Apparently
    -0.36
     pretty
    -0.36
    POSITIVE LOGITS
    SequentialGroup
    0.96
    PRNewswire
    0.93
    DockStyle
    0.82
     متعلقه
    0.80
    Jeografia
    0.79
    Geplaatst
    0.76
    cesz
    0.76
    ScopeManager
    0.76
    Datuak
    0.75
    rungsseite
    0.75
    Activations Density 2.399%

    No Known Activations