© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11981
    Prev
    Next
    INDEX
    Explanations

    positive sentiment about an idea or suggestion

    oai_token-act-pair · gemini-2.0-flash

    discussing ideas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     idea
    -2.89
     ideas
    -2.86
    Idea
    -2.81
     Idea
    -2.78
     Ideas
    -2.77
    Ideas
    -2.66
    idea
    -2.64
    ideas
    -2.59
     idée
    -2.31
     IDEAS
    -2.27
    POSITIVE LOGITS
    GEBURTSDATUM
    0.93
     AssemblyProduct
    0.74
    webElementGuid
    0.63
     ComVisible
    0.60
    uxxxx
    0.59
    principalTable
    0.58
    |}{$
    0.56
    ]-->
    0.55
    terbury
    0.52
     '{@
    0.52
    Activations Density 2.944%

    No Known Activations