© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8640
    Prev
    Next
    INDEX
    Explanations

    a biased tirade.

    oai_token-act-pair · gemini-2.0-flash

    Political diatribes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    AccessorTable
    -0.60
    obacter
    -0.58
    Jahres
    -0.54
    BagLayout
    -0.54
    endgroup
    -0.54
     purpoſe
    -0.54
    ں
    -0.54
     ely
    -0.54
     Jal
    -0.53
    tlement
    -0.52
    POSITIVE LOGITS
    AsUp
    0.62
     actionMode
    0.51
    tagHelperRunner
    0.50
    hasMoreElements
    0.48
    حياته
    0.47
    createStatement
    0.47
    bukkit
    0.47
    NESSEE
    0.45
    })();
    0.45
     pami
    0.44
    Activations Density 3.705%

    No Known Activations