© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7475
    Prev
    Next
    INDEX
    Explanations

    words beginning with "ob" that imply something is blocking or in the way

    oai_token-act-pair · gemini-2.0-flash

    words related to obstruction or obstructive conditions

    np_token-act-pair-logits · gpt-4o-mini

    ob

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    copyOf
    -0.54
    @[+][
    -0.52
     getchar
    -0.47
     ivelany
    -0.46
     cref
    -0.46
    feelings
    -0.45
    EndInit
    -0.44
     reproduced
    -0.44
    getSystemService
    -0.44
     ***!
    -0.44
    POSITIVE LOGITS
    出版年
    0.72
    lapsingToolbar
    0.56
    arXiv
    0.55
    Naissance
    0.55
    adaptiveStyles
    0.54
     مفص
    0.54
     calendriers
    0.53
    atories
    0.52
    irchen
    0.50
    richTextPanel
    0.50
    Activations Density 0.272%

    No Known Activations