© 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. 15339
    Prev
    Next
    INDEX
    Explanations

    code diffs and conditional code compilation blocks

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    ‐
    -1.55
    –
    -1.46
    ‑
    -1.37
     --
    -1.36
    -
    -1.32
     —
    -1.23
    ־
    -1.23
    --
    -1.10
    $-
    -1.02
    $--
    -0.98
    POSITIVE LOGITS
    ="@+
    0.66
    CrossRef
    0.63
     AttributeSet
    0.63
     doInBackground
    0.63
    zzar
    0.60
    SequentialGroup
    0.60
    úrate
    0.60
    %</
    0.60
    disposing
    0.59
    .³
    0.59
    Activations Density 4.189%

    No Known Activations