© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8090
    Prev
    Next
    INDEX
    Explanations

    UI elements from an iOS app.

    oai_token-act-pair · gemini-2.0-flash

    Numerical calculations

    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
     MatDialog
    -0.50
    RectangleBorder
    -0.47
    PYX
    -0.47
     PRD
    -0.47
     PackageManager
    -0.46
     GOG
    -0.45
     murals
    -0.44
     Ressource
    -0.44
     CGT
    -0.44
     BitmapFactory
    -0.43
    POSITIVE LOGITS
    contentLoaded
    0.84
    Autoritní
    0.72
    featureID
    0.71
     ujednoznacz
    0.68
    __":
    0.68
    }\\
    0.66
    Abitanti
    0.65
    __':
    0.65
     otomatig
    0.65
    __]
    0.63
    Activations Density 39.097%

    No Known Activations