© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15686
    Prev
    Next
    INDEX
    Explanations

    the word "I", and instances of the word "if" combined with another word

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     did
    -1.25
     went
    -1.16
     took
    -1.15
    did
    -1.10
     got
    -1.10
     Did
    -1.10
    Did
    -1.06
     gave
    -1.03
     came
    -1.00
     occurred
    -0.96
    POSITIVE LOGITS
    tvguidetime
    0.65
     مشين
    0.54
    HostException
    0.53
    Билгалдахарш
    0.52
    erdings
    0.52
    
    0.52
    écnicas
    0.50
    UnifiedTopology
    0.50
     bū
    0.49
    AlterField
    0.48
    Activations Density 1.065%

    No Known Activations