© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6917
    Prev
    Next
    INDEX
    Explanations

    capitalized words starting with 'Ste'

    oai_token-act-pair · gemini-2.0-flash

    Ste

    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
    SourceChecksum
    -0.81
     linkovi
    -0.80
    TagMode
    -0.79
    ]")]
    -0.78
     contextLoads
    -0.77
    \{\\
    -0.77
     티즈
    -0.76
    SBATCH
    -0.76
     fubject
    -0.76
    $.
    -0.76
    POSITIVE LOGITS
    ins
    0.45
    ini
    0.43
    bin
    0.41
    py
    0.41
    ley
    0.40
    if
    0.40
     stad
    0.40
    une
    0.39
    ws
    0.39
    org
    0.37
    Activations Density 0.483%

    No Known Activations