© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11299
    Prev
    Next
    INDEX
    Explanations

    angle brackets likely related to code imports

    oai_token-act-pair · gemini-2.0-flash

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     protoimpl
    -1.05
    #+#
    -0.85
    %)$
    -0.84
    transQ
    -0.83
    thâu
    -0.80
    ]++;
    -0.79
    MarshalTo
    -0.78
    Personendaten
    -0.77
    _))
    -0.73
    期刊论文
    -0.72
    POSITIVE LOGITS
    <bos>
    1.09
     végétale
    0.70
     détruit
    0.60
     détru
    0.60
     înal
    0.59
     frumos
    0.57
     seduta
    0.56
     équipée
    0.56
     invitado
    0.55
     toprak
    0.55
    Activations Density 0.212%

    No Known Activations