© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6837
    Prev
    Next
    INDEX
    Explanations

    words that often connect different elements in writing such as prepositions and conjunctions.

    oai_token-act-pair · gemini-2.0-flash

    book excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    enumii
    -0.61
     perfetta
    -0.46
    umsi
    -0.46
    horabuena
    -0.46
    KommentareTeilen
    -0.46
    SdkVersion
    -0.45
    InputLabel
    -0.44
     bygger
    -0.44
    Lago
    -0.43
    ագրություններ
    -0.43
    POSITIVE LOGITS
    SourceChecksum
    0.67
     familial
    0.63
     rage
    0.63
     alienation
    0.62
     '{@
    0.60
     family
    0.60
     kaarangay
    0.56
     loss
    0.55
     self
    0.55
    kháu
    0.55
    Activations Density 8.247%

    No Known Activations