© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2165
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers separated by dashes

    oai_token-act-pair · gemini-2.0-flash

    Hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     owed
    -0.59
     owes
    -0.57
     owe
    -0.50
    дар
    -0.49
    InstanceState
    -0.48
     due
    -0.48
    ―
    -0.47
     wireType
    -0.46
    thums
    -0.45
     some
    -0.44
    POSITIVE LOGITS
    tvguidetime
    0.84
    #+#
    0.79
     estekak
    0.77
    ActionMode
    0.75
    MigrationBuilder
    0.74
    IsContent
    0.71
    Diweddarwch
    0.66
    instancetype
    0.65
     تانيه
    0.64
    })*/
    0.63
    Activations Density 2.099%

    No Known Activations