© 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. 15918
    Prev
    Next
    INDEX
    Explanations

    the first three letters of the name "Hamlet" and words ending in "hat."

    oai_token-act-pair · gemini-2.0-flash

    Ham

    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
    +#+
    -0.61
    ChildIndex
    -0.56
     puissance
    -0.54
    BagLayout
    -0.52
     ورز
    -0.51
    putan
    -0.49
    EFIAPI
    -0.48
    jsonwebtoken
    -0.47
    ukone
    -0.47
    urre
    -0.47
    POSITIVE LOGITS
    Pautan
    0.63
    ensement
    0.55
     resourceCulture
    0.54
     Pristupljeno
    0.53
    ernoo
    0.52
    Попис
    0.52
     EPC
    0.49
    ERA
    0.49
    StoreMessageInfo
    0.48
     समीक्षाओं
    0.48
    Activations Density 0.449%

    No Known Activations