© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6942
    Prev
    Next
    INDEX
    Explanations

    math formulas and some errors in text

    oai_token-act-pair · gemini-2.0-flash

    Code, equations, file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     J
    -1.66
     JJ
    -1.60
     JA
    -1.58
     j
    -1.56
    J
    -1.55
     JC
    -1.51
     JE
    -1.50
     JB
    -1.48
     JL
    -1.46
     JT
    -1.46
    POSITIVE LOGITS
     disambiguazione
    0.42
    wną
    0.36
    SharedCtor
    0.36
    zbęd
    0.35
    ourg
    0.34
    ualla
    0.33
    trzyma
    0.33
    čnih
    0.33
    garek
    0.33
    cení
    0.33
    Activations Density 1.997%

    No Known Activations