© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12305
    Prev
    Next
    INDEX
    Explanations

    code-related tokens, especially those appearing in PHP-like code

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    WriteBarrier
    -0.69
    Према
    -0.58
    bootstrapcdn
    -0.54
    ItemBackground
    -0.50
     egli
    -0.50
     correctes
    -0.46
     stabilisation
    -0.45
    aliyun
    -0.45
     numerals
    -0.43
    BufferException
    -0.43
    POSITIVE LOGITS
    tvguidetime
    0.60
    enciaga
    0.57
    ]").
    0.54
    }}}}
    0.52
    dimos
    0.51
     kaarangay
    0.51
    _))
    0.50
     Roskov
    0.50
    })));
    0.50
    ULTURA
    0.49
    Activations Density 3.327%

    No Known Activations