© 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. 13028
    Prev
    Next
    INDEX
    Explanations

    code blocks and code indentations

    oai_token-act-pair · gemini-2.0-flash

    Non-English and 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_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
    Personendaten
    -0.81
    RetentionPolicy
    -0.71
    DockStyle
    -0.63
    enumii
    -0.54
    OwnProperty
    -0.54
    taz
    -0.50
    richTextPanel
    -0.49
     phát
    -0.48
     s
    -0.48
     pal
    -0.48
    POSITIVE LOGITS
     bershka
    0.69
     Мексичка
    0.69
     fevere
    0.68
     Савезне
    0.63
     Majefty
    0.60
     Monfieur
    0.60
     faſt
    0.58
    ształ
    0.58
    })));
    0.57
    ſelves
    0.57
    Activations Density 0.300%

    No Known Activations