© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3980
    Prev
    Next
    INDEX
    Explanations

    language from academic research papers

    oai_token-act-pair · gemini-2.0-flash

    academic research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    RegistryLite
    -0.67
    kloped
    -0.58
     NSCoder
    -0.57
    findpost
    -0.55
     Roskov
    -0.55
    \{\\
    -0.55
    ніципалі
    -0.53
    Hauptartikel
    -0.52
    ⓘ
    -0.51
    tonode
    -0.50
    POSITIVE LOGITS
    PerformLayout
    0.56
     masking
    0.52
     Enlight
    0.49
    Initializable
    0.49
     mask
    0.48
    Demikian
    0.48
     elkaar
    0.47
     masks
    0.47
     masked
    0.46
    _));
    0.45
    Activations Density 3.231%

    No Known Activations