© 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. 4605
    Prev
    Next
    INDEX
    Explanations

    verbs related to assessment, constraints, and influence

    oai_token-act-pair · gemini-2.0-flash

    effects and evaluations

    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
     ProtoMessage
    -0.65
    });
    -0.60
    </tfoot>
    -0.60
    Билгалдахарш
    -0.58
    렀
    -0.57
     be
    -0.56
    istoitu
    -0.55
    ++);
    -0.55
     normaux
    -0.55
    ).—
    -0.54
    POSITIVE LOGITS
    expandindo
    0.70
     <>",
    0.68
     Paglinawan
    0.62
    makeText
    0.62
    iestety
    0.61
    🏾
    0.58
    FromArgb
    0.57
    　
    0.57
     despised
    0.56
    OptionsMenu
    0.56
    Activations Density 1.444%

    No Known Activations