© 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. 15480
    Prev
    Next
    INDEX
    Explanations

    usages of the word "back" and similar words involved in processes

    oai_token-act-pair · gemini-2.0-flash

    legal/political discussions

    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
     '
    -0.62
     we
    -0.60
     des
    -0.59
     no
    -0.59
     pes
    -0.58
     dis
    -0.57
     cho
    -0.57
     mer
    -0.57
     be
    -0.56
     reg
    -0.56
    POSITIVE LOGITS
    findpost
    1.26
    AndEndTag
    1.22
     Shakspeare
    1.14
     Cæsar
    1.12
     Houſe
    1.07
     ſeveral
    1.02
     hierogly
    1.01
     itſelf
    0.98
     Reſ
    0.97
     Monfieur
    0.96
    Activations Density 1.675%

    No Known Activations