© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12963
    Prev
    Next
    INDEX
    Explanations

    the word "is" as well as the words "this", "be", "are", "program", and "software".

    oai_token-act-pair · gemini-2.0-flash

    is or was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ètement
    -0.49
     Vikipedi
    -0.49
     Meksiku
    -0.48
     Namely
    -0.46
    ValueStyle
    -0.46
    ----</
    -0.45
    :+:
    -0.44
    principalTable
    -0.43
     transfieras
    -0.42
    SerializedName
    -0.42
    POSITIVE LOGITS
     kasarigan
    0.61
     FetchType
    0.59
    ighbor
    0.59
    الإنجليزية
    0.58
    rétaire
    0.56
    _
    0.56
    |}{$
    0.54
    }{%
    0.54
    AddTagHelper
    0.52
    EFIAPI
    0.52
    Activations Density 1.701%

    No Known Activations