© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3196
    Prev
    Next
    INDEX
    Explanations

    the word "for" and, less confidently, time-related words and the word "been."

    oai_token-act-pair · gemini-2.0-flash

    for

    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
     فريبيس
    -1.11
     GenerationType
    -1.10
     Efq
    -1.02
     snippetHide
    -1.01
     disambiguazione
    -0.98
     Jefus
    -0.98
    Portály
    -0.97
    TemporalType
    -0.95
    ſelf
    -0.94
    AutoScaleMode
    -0.94
    POSITIVE LOGITS
     over
    0.66
    over
    0.60
     the
    0.57
     so
    0.47
    r
    0.45
    Over
    0.45
     at
    0.44
     y
    0.43
    ↵↵
    0.43
    rs
    0.43
    Activations Density 3.095%

    No Known Activations