© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14852
    Prev
    Next
    INDEX
    Explanations

    pronouns and auxiliary verbs in a sentence with prepositions like "to" and "from".

    oai_token-act-pair · gemini-2.0-flash

    go

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     kasarigan
    -1.14
    ValueStyle
    -0.92
    tvguidetime
    -0.91
     cherchés
    -0.91
    RenderAtEndOf
    -0.85
     виправивши
    -0.85
    abestanden
    -0.84
    parsedMessage
    -0.82
     ExecuteAsync
    -0.82
    verwijspagina
    -0.81
    POSITIVE LOGITS
     go
    2.28
     goes
    2.09
     going
    1.80
     Go
    1.77
     went
    1.73
    go
    1.73
    Go
    1.73
    goes
    1.73
     Going
    1.67
    Going
    1.64
    Activations Density 2.276%

    No Known Activations