© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16214
    Prev
    Next
    INDEX
    Explanations

    words or phrases that indicate someone is trying to evade legal prosecution

    oai_token-act-pair · gemini-2.0-flash

    Legal trouble

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    SpringBootTest
    -0.58
    #+#
    -0.56
     oprot
    -0.56
    SupportActionBar
    -0.56
     InputDecoration
    -0.55
    قایناقلار
    -0.54
    ListItemIcon
    -0.54
     đ
    -0.52
     WaitForSeconds
    -0.52
    AppMethodBeat
    -0.51
    POSITIVE LOGITS
    prisma
    0.56
    principalColumn
    0.54
    GraphicsUnit
    0.52
    ourcen
    0.51
    клопе
    0.47
    isers
    0.47
    реса
    0.47
    PrototypeOf
    0.46
     menye
    0.44
    yorsunuz
    0.44
    Activations Density 9.316%

    No Known Activations