© 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. 7337
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to insects being attracted and killed

    oai_token-act-pair · gemini-2.0-flash

    insects and elimination

    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
    __":
    -0.71
     незавершена
    -0.69
    Vidite
    -0.66
     مرئيه
    -0.66
    󠁴
    -0.66
     NAA
    -0.66
     numberOfRows
    -0.63
     noqa
    -0.63
    tamount
    -0.60
    cheme
    -0.59
    POSITIVE LOGITS
     sauvages
    0.43
    __(/*!
    0.42
     religieuses
    0.41
     connues
    0.41
     raggiunto
    0.41
     présentes
    0.41
     malheure
    0.40
     humains
    0.40
     der
    0.40
     vacanza
    0.40
    Activations Density 1.385%

    No Known Activations