© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13251
    Prev
    Next
    INDEX
    Explanations

    words indicating a judgement or support in a legal or software support context

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Support
    -3.11
     Support
    -3.11
     supporting
    -3.09
     supported
    -3.02
     Supporting
    -3.00
     support
    -3.00
    support
    -2.95
    Supporting
    -2.95
    supporting
    -2.92
     SUPPORT
    -2.89
    POSITIVE LOGITS
    hões
    0.38
    Precautionary
    0.38
    openqa
    0.38
    ankin
    0.37
     incomplète
    0.37
    ↩
    0.36
    haden
    0.36
    ływ
    0.35
    boxy
    0.35
    약
    0.35
    Activations Density 3.044%

    No Known Activations