© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15695
    Prev
    Next
    INDEX
    Explanations

    the word "this" and words associated with medical care or reporting

    oai_token-act-pair · 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
    Negative Logits
    <bos>
    -1.06
    sizeCache
    -0.68
    GraphicsUnit
    -0.67
    AndEndTag
    -0.63
    enterOuterAlt
    -0.61
    المشاركات
    -0.61
    tvguidetime
    -0.60
    ########.
    -0.60
    </caption>
    -0.60
     ***!
    -0.57
    POSITIVE LOGITS
    kranz
    0.45
     GenerationType
    0.42
    armament
    0.42
    ResumeLayout
    0.42
    BASELINE
    0.40
    ectl
    0.40
    ように
    0.40
    ◄
    0.40
    AxisSize
    0.40
     específico
    0.40
    Activations Density 1.525%

    No Known Activations