© 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. 11207
    Prev
    Next
    INDEX
    Explanations

    uses of the words "when","is", personal pronouns and words relating to computer applications

    oai_token-act-pair · 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
     nicht
    -1.11
     niet
    -1.00
     keineswegs
    -0.97
     not
    -0.96
     não
    -0.94
     ikke
    -0.94
     wasn
    -0.89
     bukan
    -0.89
     weren
    -0.88
    ]!=
    -0.85
    POSITIVE LOGITS
     is
    0.71
     are
    0.52
     Is
    0.37
    randrange
    0.36
     ahor
    0.36
    __;
    0.36
    Is
    0.35
    的是
    0.35
    Initializable
    0.35
     was
    0.34
    Activations Density 1.598%

    No Known Activations