© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11783
    Prev
    Next
    INDEX
    Explanations

    a mix of words relating to bad things paired with words representing indices or locations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    webElementXpaths
    -0.85
    httphttps
    -0.78
     nakalista
    -0.77
     Baillargeon
    -0.76
    +#+#
    -0.76
     виправивши
    -0.75
    UnsafeEnabled
    -0.71
    findpost
    -0.71
    sizeCache
    -0.71
    InjectAttribute
    -0.70
    POSITIVE LOGITS
    ?,?,
    0.59
     Ch
    0.51
    AllowAnonymous
    0.47
     Sch
    0.46
     Me
    0.46
     transfer
    0.45
    後は
    0.45
     He
    0.44
    Endpoints
    0.44
    wich
    0.43
    Activations Density 0.912%

    No Known Activations