© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11449
    Prev
    Next
    INDEX
    Explanations

    LaTeX code

    oai_token-act-pair · gemini-2.0-flash

    backslashes

    np_token-act-pair-logits · gpt-4o-mini

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     tartalomajánló
    -0.66
    ertale
    -0.66
    }))
    -0.56
    ANCHE
    -0.55
    onsored
    -0.55
     doubtnut
    -0.55
    apkamer
    -0.55
     Abar
    -0.54
     CURIAM
    -0.54
     ་་
    -0.54
    POSITIVE LOGITS
    findpost
    0.66
    setcounter
    0.59
    CrossRef
    0.59
    x
    0.56
     disponibilités
    0.50
     Lightboxes
    0.48
    الدراسه
    0.47
     suck
    0.46
    CppMethod
    0.46
     calendriers
    0.46
    Activations Density 0.184%

    No Known Activations