© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10931
    Prev
    Next
    INDEX
    Explanations

    language related to problem-solving, medical/technical research, saving, helping prevent, and improving.

    oai_token-act-pair · gemini-2.0-flash

    Mitigation/Prevention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    complexContent
    -0.91
    StoryboardSegue
    -0.88
    AnchorTagHelper
    -0.84
    __":
    -0.84
    tvguidetime
    -0.82
    __':
    -0.81
    __':
    -0.80
    __*/
    -0.73
    EndInit
    -0.72
    ContentAsync
    -0.71
    POSITIVE LOGITS
    <bos>
    0.98
     high
    0.47
    ’
    0.46
     russischen
    0.46
     phút
    0.45
     hành
    0.44
    な
    0.44
    ↵
    0.43
     Brazilian
    0.43
     sauter
    0.43
    Activations Density 3.064%

    No Known Activations