© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10757
    Prev
    Next
    INDEX
    Explanations

    references to where someone or something is located or what they are doing

    oai_token-act-pair · gemini-2.0-flash

    syntax patterns related to location or context

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

    here/there

    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
     Here
    -0.87
     here
    -0.84
    here
    -0.80
    Here
    -0.78
     ici
    -0.73
    softc
    -0.72
     HERE
    -0.71
     aquí
    -0.68
    在这里
    -0.67
     Здесь
    -0.67
    POSITIVE LOGITS
     with
    0.51
     RIPRODUZIONE
    0.50
     civiles
    0.49
    ictwo
    0.49
     attravers
    0.48
     religieuse
    0.47
    CopyWith
    0.45
     sauvage
    0.45
     civile
    0.44
    awaiter
    0.44
    Activations Density 18.304%

    No Known Activations