© 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. 6271
    Prev
    Next
    INDEX
    Explanations

    misspellings, gibberish, and also references (e.g. papers).

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
    ulina
    -0.46
    itya
    -0.46
    ingo
    -0.45
    ungere
    -0.43
    тесь
    -0.42
    aa
    -0.40
    ǔ
    -0.40
    urou
    -0.40
    voort
    -0.40
    indra
    -0.39
    POSITIVE LOGITS
     تضيفلها
    0.68
    aph
    0.59
    Personensuche
    0.58
     دیکھیے
    0.57
    цездатний
    0.57
    amet
    0.56
    amel
    0.54
    alien
    0.53
    anz
    0.52
    anii
    0.52
    Activations Density 0.685%

    No Known Activations