© 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. 3984
    Prev
    Next
    INDEX
    Explanations

    transition words and discourse markers, like "but", "rather", and ways to introduce a subject

    oai_token-act-pair · gemini-2.0-flash

    words indicating contrast or alternatives

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

    but

    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
    <bos>
    -0.61
     Infórmanos
    -0.54
     pourrais
    -0.53
    Bibliograf
    -0.46
     Anf
    -0.46
    seguida
    -0.46
    cées
    -0.45
     Pigeon
    -0.43
    Pigeon
    -0.43
     nzuri
    -0.42
    POSITIVE LOGITS
     instead
    3.64
    instead
    3.38
    Instead
    3.22
     Instead
    3.17
     вместо
    2.53
     rather
    2.38
     istället
    2.30
     zamiast
    2.30
    rather
    2.22
    Rather
    2.20
    Activations Density 7.279%

    No Known Activations