© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 13302
    Prev
    Next
    INDEX
    Explanations

    words enclosed in asterisks and sometimes other mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    code/formulas/symbols

    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
    ).
    -2.44
    ”.
    -2.30
    ".
    -2.30
    ").
    -2.16
    ].
    -2.06
    ”).
    -2.05
    “.
    -2.02
    ».
    -2.00
    .).
    -2.00
    .”
    -1.99
    POSITIVE LOGITS
    },[])
    0.60
     Offisielt
    0.60
    /**
    0.56
    ֗
    0.53
     Мексичка
    0.52
     Roskov
    0.52
    GHIJKLM
    0.50
    reszcie
    0.49
    HostException
    0.48
    setupUi
    0.45
    Activations Density 13.129%

    No Known Activations