© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8069
    Prev
    Next
    INDEX
    Explanations

    words related to legal and medical documents

    oai_token-act-pair · gemini-2.0-flash

    technical/mixed content

    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
    AndEndTag
    -0.72
    ConstraintMaker
    -0.61
    noinspection
    -0.59
    Koordinaten
    -0.56
    \{\\
    -0.56
     opérés
    -0.55
     ffilmiau
    -0.54
     المعيارى
    -0.53
    </thead>
    -0.51
     paramString
    -0.50
    POSITIVE LOGITS
     intptr
    0.69
    GeneratedCode
    0.58
    PRNewswire
    0.54
    scriptcase
    0.54
     Privacidade
    0.53
     Bourgoin
    0.50
     Winaray
    0.50
    ########.
    0.49
    GeneratedMessage
    0.48
    Datuak
    0.45
    Activations Density 0.533%

    No Known Activations