© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2914
    Prev
    Next
    INDEX
    Explanations

    named entities and locations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Personendaten
    -0.65
    ThroughAttribute
    -0.64
     consultato
    -0.63
    VIAF
    -0.57
    قایناقلار
    -0.53
    ########.
    -0.52
     penetration
    -0.52
    </thead>
    -0.50
    MigrationBuilder
    -0.49
    Sklici
    -0.49
    POSITIVE LOGITS
    astéroïdes
    0.74
    encodeWith
    0.61
     yPos
    0.57
     Arrays
    0.55
    pieler
    0.54
    ніципа
    0.54
     itemView
    0.54
    Попис
    0.53
    PONE
    0.53
     getattr
    0.52
    Activations Density 4.560%

    No Known Activations