© 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. 13720
    Prev
    Next
    INDEX
    Explanations

    fantasy/martial arts style action words.

    oai_token-act-pair · gemini-2.0-flash

    technical or programming-related terms

    np_token-act-pair-logits · gpt-4o-mini
    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
     فريبيس
    -0.86
     transférez
    -0.70
    省市镇
    -0.69
     transfieras
    -0.68
     onOptions
    -0.66
     ErrIntOverflow
    -0.66
    ::_('
    -0.65
     Мексичка
    -0.60
     Polres
    -0.58
    tichetta
    -0.58
    POSITIVE LOGITS
    #+#
    0.65
     BorderRadius
    0.55
     esboço
    0.51
    otropy
    0.50
     snippetHide
    0.49
    yang
    0.43
    urrection
    0.43
    uluk
    0.43
    NDA
    0.43
     pus
    0.42
    Activations Density 0.445%

    No Known Activations