© 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. 1730
    Prev
    Next
    INDEX
    Explanations

    a few categories - music groups with the word "boys" in their name, items related to the military, words related to municipalities, and a few seemingly random words.

    oai_token-act-pair · gemini-2.0-flash

    beach

    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
     Beach
    -1.85
    Beach
    -1.70
     beach
    -1.69
    beach
    -1.59
     BEACH
    -1.55
     beaches
    -1.11
     Beaches
    -1.05
     beachfront
    -0.90
     praia
    -0.87
     seashore
    -0.84
    POSITIVE LOGITS
     يتيمه
    0.76
    tonode
    0.70
     <",
    0.65
    NUMX
    0.65
    MigrationBuilder
    0.61
     المعيارى
    0.61
    </thead>
    0.59
    MergeFrom
    0.57
    migrationBuilder
    0.56
    ($__
    0.56
    Activations Density 5.982%

    No Known Activations