© 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. 6235
    Prev
    Next
    INDEX
    Explanations

    Arabic or Japanese words

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    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
     Cæsar
    -0.45
     Mahomet
    -0.45
     ſein
    -0.44
     enfans
    -0.44
     Shakspeare
    -0.42
     Shaksp
    -0.42
     quelcon
    -0.42
     démocr
    -0.42
     avoient
    -0.41
     leaſt
    -0.41
    POSITIVE LOGITS
     is
    0.26
     betweenstory
    0.26
     across
    0.24
     the
    0.23
     implements
    0.22
    UrlResolution
    0.22
     importantly
    0.22
     this
    0.22
     on
    0.22
     understanding
    0.22
    Activations Density 0.234%

    No Known Activations