© 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. 13856
    Prev
    Next
    INDEX
    Explanations

    words describing communication, contribution, and inspiration.

    oai_token-act-pair · gemini-2.0-flash

    content involving sharing personal experiences and stories

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

    share

    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
     يتيمه
    -0.82
    @[+][
    -0.70
     """
    -0.63
     disambiguazione
    -0.61
    numerusform
    -0.60
     Catawiki
    -0.55
     faſt
    -0.54
     antemano
    -0.53
    ValueStyle
    -0.53
    httphttps
    -0.53
    POSITIVE LOGITS
     propOrder
    0.71
     an
    0.54
    ,
    0.46
     bando
    0.45
     the
    0.44
     out
    0.44
    Digitized
    0.43
    жению
    0.43
     w
    0.43
     with
    0.43
    Activations Density 6.182%

    No Known Activations