© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14043
    Prev
    Next
    INDEX
    Explanations

    words relating to software or hardware technical documentation

    oai_token-act-pair · gemini-2.0-flash

    Technical/scientific text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Meksiku
    -0.68
    <bos>
    -0.63
    ngdoc
    -0.58
    Бахар
    -0.55
    گاب
    -0.54
     henvisninger
    -0.52
     سكانية
    -0.51
    ranza
    -0.50
    bidities
    -0.48
     @"/
    -0.47
    POSITIVE LOGITS
     greateſt
    0.78
     Jefus
    0.73
     purpoſe
    0.72
     pleaſure
    0.70
     Houſe
    0.70
     Theſe
    0.67
     ſame
    0.65
     ſtate
    0.64
     houſe
    0.63
     preſent
    0.62
    Activations Density 1.415%

    No Known Activations