© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11532
    Prev
    Next
    INDEX
    Explanations

    words relating to computer security and malicious attacks

    oai_token-act-pair · gemini-2.0-flash

    phishing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ΡΙ
    -0.63
    ($__
    -0.52
    Carriera
    -0.52
     unknownFields
    -0.51
    FetchType
    -0.47
    тература
    -0.47
     FBref
    -0.47
    ές
    -0.47
    kuuta
    -0.44
     nakalista
    -0.43
    POSITIVE LOGITS
    الحياه
    0.62
    كويكب
    0.55
    frameCount
    0.53
     विश्वसनीयता
    0.52
     glycine
    0.51
    WebVitals
    0.51
    igshid
    0.51
     propOrder
    0.51
     ESF
    0.51
    dement
    0.50
    Activations Density 0.356%

    No Known Activations