© 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. 4282
    Prev
    Next
    INDEX
    Explanations

    words that are components of code or programming languages

    oai_token-act-pair · gemini-2.0-flash

    say open parenthesis

    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
    InitVars
    -0.65
    seamnă
    -0.65
     ویکی‌پدیا
    -0.60
     Reverso
    -0.60
    Vidite
    -0.59
     itſelf
    -0.57
    wahati
    -0.56
    إنه
    -0.55
     Савезне
    -0.54
    <bos>
    -0.53
    POSITIVE LOGITS
    )
    1.33
    ).
    1.30
    ),
    1.27
    )?
    1.16
    .)
    1.16
    ):
    1.13
    ?)
    1.11
    ())
    1.07
    ?).
    1.05
    ?),
    1.04
    Activations Density 5.415%

    No Known Activations