© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3221
    Prev
    Next
    INDEX
    Explanations

    the word "here", as well as words related to bad outcomes

    oai_token-act-pair · gemini-2.0-flash

    the word "here"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     contextLoads
    -0.63
     متعلقه
    -0.61
    ArgsConstructor
    -0.59
    abang
    -0.57
    IBOutlet
    -0.57
     AssemblyVersion
    -0.56
    cloudflare
    -0.54
    Portale
    -0.54
    expandindo
    -0.53
     renewals
    -0.53
    POSITIVE LOGITS
    ,
    0.49
    .
    0.49
    alah
    0.44
    ↵↵
    0.44
    <bos>
    0.44
    pok
    0.43
     too
    0.42
    ihnachts
    0.41
     veneta
    0.41
     acceptez
    0.40
    Activations Density 9.307%

    No Known Activations