© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4742
    Prev
    Next
    INDEX
    Explanations

    URLs or parts of URLs

    oai_token-act-pair · gemini-2.0-flash

    URLs and links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     useAuth
    -0.63
    RenderAtEndOf
    -0.62
    PyTuple
    -0.56
    RegressionTest
    -0.56
     TRAP
    -0.55
    ❋
    -0.54
     تانيه
    -0.54
    ">//
    -0.54
     Jasa
    -0.53
    Rhestr
    -0.52
    POSITIVE LOGITS
    photobucket
    0.66
     defaultstate
    0.64
    ppins
    0.60
     Audiodateien
    0.53
    VersionUID
    0.51
     dépos
    0.50
    مصادر
    0.48
     Infor
    0.48
     serez
    0.47
     dessinée
    0.46
    Activations Density 0.532%

    No Known Activations