© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13069
    Prev
    Next
    INDEX
    Explanations

    text discussing understanding and managing something

    oai_token-act-pair · gemini-2.0-flash

    understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     roll
    -0.52
     send
    -0.52
     take
    -0.52
     Take
    -0.47
     same
    -0.46
     following
    -0.43
     ли
    -0.43
     Hark
    -0.42
    ke
    -0.42
    .
    -0.42
    POSITIVE LOGITS
     Efq
    1.16
     myſelf
    1.04
     AssemblyCulture
    0.96
    ]--;
    0.93
    MLLoader
    0.91
    )");
    0.91
     Eſ
    0.88
    tvguidetime
    0.87
     itſelf
    0.87
     ujednoznacz
    0.86
    Activations Density 2.852%

    No Known Activations