© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9895
    Prev
    Next
    INDEX
    Explanations

    code snippets with calls to an api to update content and related data

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    AddTagHelper
    -0.65
     للمعارف
    -0.59
    StoreMessageInfo
    -0.56
    moiselle
    -0.53
     intptr
    -0.52
     tslint
    -0.52
     JAKARTA
    -0.50
    DrawerToggle
    -0.49
     الحره
    -0.48
    StoryboardSegue
    -0.48
    POSITIVE LOGITS
    tvguidetime
    0.65
    Bearing
    0.60
     Bearing
    0.59
    impri
    0.58
    CRITICAL
    0.56
    mintaan
    0.56
     terza
    0.56
    elus
    0.56
     palsu
    0.55
     définiti
    0.54
    Activations Density 5.599%

    No Known Activations