© 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. 11407
    Prev
    Next
    INDEX
    Explanations

    currency amounts and real estate listings

    oai_token-act-pair · gemini-2.0-flash

    property listings and associated metadata

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

    prices and sales

    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
     AttributeSet
    -0.66
     itſelf
    -0.66
     ftate
    -0.63
     myſelf
    -0.63
     ſeveral
    -0.63
     FetchType
    -0.63
    Autoritní
    -0.62
     Monfieur
    -0.62
     skeletons
    -0.61
     doubtnut
    -0.61
    POSITIVE LOGITS
    Nationalité
    0.52
     di
    0.50
     n
    0.48
    +#+#
    0.47
     des
    0.47
     re
    0.46
     du
    0.46
     error
    0.46
     course
    0.45
    tvguidetime
    0.45
    Activations Density 2.685%

    No Known Activations