© 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. 10514
    Prev
    Next
    INDEX
    Explanations

    clauses where other people are talking about a third party

    oai_token-act-pair · gemini-2.0-flash

    were

    np_max-act-logits · 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
     extremely
    -1.85
     quite
    -1.73
    Very
    -1.70
    extremely
    -1.68
    quite
    -1.68
     VERY
    -1.63
     very
    -1.62
    Extremely
    -1.62
     Very
    -1.61
     Extremely
    -1.61
    POSITIVE LOGITS
     '\\;'
    0.56
    makeConstraints
    0.56
    webElementXpaths
    0.50
    CreateInfo
    0.47
    ']").
    0.46
    }")]
    0.45
    rinfo
    0.44
     }]
    0.43
    })()
    0.42
    +#+#
    0.42
    Activations Density 1.768%

    No Known Activations