© 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. 8745
    Prev
    Next
    INDEX
    Explanations

    various forms of numbers and related concepts

    oai_token-act-pair · gemini-2.0-flash

    references to axes or channels

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

    robotics and flight controllers

    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
    principalColumn
    -0.82
     intptr
    -0.65
     kubwa
    -0.60
     thinning
    -0.56
     Paglinawan
    -0.54
    mergeFrom
    -0.53
    bootstrapcdn
    -0.53
    bewerken
    -0.53
     étoient
    -0.52
     المعيارى
    -0.52
    POSITIVE LOGITS
    NewUrlParser
    0.58
    axis
    0.57
     axis
    0.53
    CHANNELS
    0.52
    AXIS
    0.51
    bank
    0.51
    ormány
    0.51
    cipar
    0.49
     vira
    0.49
     analog
    0.49
    Activations Density 2.423%

    No Known Activations