© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 12802
    Prev
    Next
    INDEX
    Explanations

    evaluative and relational words, often in the context of comparisons and correctness

    oai_token-act-pair · gemini-2.0-flash

    Opinions and judgments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    expandindo
    -0.65
     GenerationType
    -0.64
    TimeTo
    -0.55
    aryen
    -0.53
     spectacles
    -0.53
     tartalomajánló
    -0.52
    almi
    -0.52
    pięk
    -0.52
    FOLIO
    -0.51
     eterno
    -0.50
    POSITIVE LOGITS
     saites
    0.72
    oredCriteria
    0.72
     entrambi
    0.70
    AutoScaleMode
    0.65
    Both
    0.65
     Both
    0.63
    îtra
    0.63
    both
    0.63
     both
    0.62
    });*/
    0.61
    Activations Density 1.122%

    No Known Activations