© 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. 11633
    Prev
    Next
    INDEX
    Explanations

    capitalized words and acronyms, especially at the beginnings of phrases and sentences

    oai_token-act-pair · gemini-2.0-flash

    Formal/structured text

    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
     يتيمه
    -0.67
    APORE
    -0.65
    unately
    -0.63
    )++;
    -0.63
    --)
    -0.59
    DockStyle
    -0.59
    })*/
    -0.59
    ̓
    -0.59
    AndEndTag
    -0.59
     تانيه
    -0.59
    POSITIVE LOGITS
    Personendaten
    0.40
    Zap
    0.37
     ERSITY
    0.35
    Cas
    0.35
     CiNii
    0.35
    Pz
    0.35
     PUL
    0.34
    Ṣ
    0.33
     е
    0.33
    Té
    0.33
    Activations Density 1.570%

    No Known Activations