© 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. 2093
    Prev
    Next
    INDEX
    Explanations

    patterns of articles, common adjectives, and the verb 'to be'.

    oai_token-act-pair · gemini-2.0-flash

    the term "common"

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

    common

    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
     goes
    -1.35
     go
    -1.17
    goes
    -1.14
     Goes
    -1.13
    Goes
    -1.04
     went
    -0.98
     GOES
    -0.98
    go
    -0.90
    Go
    -0.90
     gone
    -0.86
    POSITIVE LOGITS
     common
    0.84
    common
    0.71
     normal
    0.60
     natural
    0.58
    AnchorStyles
    0.57
    #
    0.56
     Common
    0.56
    Common
    0.56
     comunes
    0.55
     COMMON
    0.55
    Activations Density 1.302%

    No Known Activations