© 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. 1967
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially place names and organizations, often associated with the beginning of the word

    oai_token-act-pair · gemini-2.0-flash

    Irish locations/saints

    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
    uk
    -0.49
    uck
    -0.41
    Zunanje
    -0.40
    ãng
    -0.40
     astore
    -0.40
    undet
    -0.40
    dieux
    -0.40
     Pfund
    -0.39
     accesso
    -0.39
    tida
    -0.39
    POSITIVE LOGITS
    SequentialGroup
    0.68
     Forumite
    0.66
    
    0.65
    Réponse
    0.65
     daarvoor
    0.64
    TargetException
    0.63
     onPostExecute
    0.60
     doubtnut
    0.59
     مشين
    0.58
    ArrowToggle
    0.58
    Activations Density 0.444%

    No Known Activations