© 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. 9542
    Prev
    Next
    INDEX
    Explanations

    a variety of words that appear to be from legal, geographical, scientific, or technical documents.

    oai_token-act-pair · gemini-2.0-flash

    legal/technical documents

    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
     under
    -0.42
     numbers
    -0.42
     aimable
    -0.41
     willkommen
    -0.40
    énération
    -0.40
     共
    -0.39
    ctober
    -0.38
    thul
    -0.37
     hóspedes
    -0.36
     here
    -0.35
    POSITIVE LOGITS
    IUrlHelper
    1.34
     NSCoder
    0.97
    StoryboardSegue
    0.96
    MigrationBuilder
    0.93
    tagHelperRunner
    0.92
    +#+#
    0.88
    principalColumn
    0.84
    ⓧ
    0.82
    IndentedString
    0.80
    UnitTesting
    0.79
    Activations Density 5.727%

    No Known Activations