© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5078
    Prev
    Next
    INDEX
    Explanations

    sentences that express a lack or deficiency

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    XMLSchema
    -0.55
    AndEndTag
    -0.52
    ρυσ
    -0.48
     dépla
    -0.47
    teck
    -0.47
    numerusform
    -0.45
     Mero
    -0.45
     Diſ
    -0.44
    subpackage
    -0.44
    boro
    -0.44
    POSITIVE LOGITS
     createState
    0.60
     ويكيميديا
    0.58
    tagext
    0.56
    rupulous
    0.54
    PyExc
    0.52
    igraphy
    0.52
    fjspx
    0.52
     Eligible
    0.50
    chillo
    0.48
     LEYENDO
    0.48
    Activations Density 4.070%

    No Known Activations