© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7517
    Prev
    Next
    INDEX
    Explanations

    things that cause disagreement or conflict

    oai_token-act-pair · gemini-2.0-flash

    contradictions and conflicts

    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
     conflict
    -2.38
     Conflict
    -2.28
     conflicts
    -2.17
    Conflict
    -2.13
    conflict
    -2.11
     Conflicts
    -2.05
     conflit
    -1.75
     Konflikt
    -1.68
     conflicto
    -1.68
     clash
    -1.67
    POSITIVE LOGITS
    IndentedString
    0.53
    다는
    0.48
    VertexAttrib
    0.46
     Daerah
    0.45
     smar
    0.45
    ậm
    0.45
    antwoorde
    0.44
    Tage
    0.44
    permitAll
    0.44
    铵
    0.44
    Activations Density 2.247%

    No Known Activations