© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9907
    Prev
    Next
    INDEX
    Explanations

    named entities of places, sports titles, and organizations

    oai_token-act-pair · gemini-2.0-flash

    Cities/locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    KommentareTeilen
    -0.79
     utafitiHapana
    -0.65
    OGND
    -0.64
    LElement
    -0.61
    AccessorTable
    -0.60
    AutoScaleMode
    -0.57
    raspberry
    -0.55
     الاطلاع
    -0.55
    photobucket
    -0.55
    UserScript
    -0.53
    POSITIVE LOGITS
    fti
    0.52
    __(/*!
    0.51
    gas
    0.49
     umane
    0.48
    dero
    0.47
    วัติ
    0.46
    poto
    0.45
    ilmente
    0.44
     Mox
    0.44
     gas
    0.44
    Activations Density 0.973%

    No Known Activations