© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4164
    Prev
    Next
    INDEX
    Explanations

    the word 'chat' and sometimes finds words synonymous to communicating

    oai_token-act-pair · gemini-2.0-flash

    chat

    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
    gan
    -0.66
    ers
    -0.62
    ля
    -0.61
    ,”
    -0.61
    zing
    -0.60
    ing
    -0.60
    cu
    -0.59
    )$-
    -0.59
    sten
    -0.59
    ↵↵
    -0.57
    POSITIVE LOGITS
     themſelves
    1.16
     Majefty
    1.09
     himſelf
    1.09
     anſ
    1.08
     Jefus
    1.06
     houſe
    1.06
     poffe
    1.03
     Efq
    1.02
     neceff
    1.02
     myſelf
    1.02
    Activations Density 1.511%

    No Known Activations