© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14576
    Prev
    Next
    INDEX
    Explanations

    HTML markup attributes and tags related to styling and structure

    oai_token-act-pair · gemini-2.0-flash

    HTML class attributes

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

    class

    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
    porre
    -0.58
     «
    -0.56
     name
    -0.56
     &=
    -0.53
    <eos>
    -0.53
     الرياضيه
    -0.52
    Portale
    -0.49
    avras
    -0.48
     McP
    -0.48
     Infórmanos
    -0.47
    POSITIVE LOGITS
     Efq
    0.79
     Theſe
    0.73
     itſelf
    0.71
     ſeveral
    0.66
     myſelf
    0.66
     Савезне
    0.66
     raiſ
    0.65
     ―――――
    0.63
    berdayakan
    0.60
    ientôt
    0.58
    Activations Density 0.335%

    No Known Activations