© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11487
    Prev
    Next
    INDEX
    Explanations

    code blocks with Java-like syntax, possibly related to getters and setters

    oai_token-act-pair · gemini-2.0-flash

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     [],
    -0.55
     {},
    -0.54
    Hentet
    -0.52
    }}}}
    -0.52
     [{
    -0.51
    ".
    -0.49
     Sternen
    -0.49
    رشف
    -0.47
     ]
    -0.47
    `
    -0.46
    POSITIVE LOGITS
    LookAnd
    0.67
    Geplaatst
    0.63
    Дереккөздер
    0.62
    Brainz
    0.60
    phorus
    0.60
     виправивши
    0.59
    TintMode
    0.57
    COUVER
    0.56
    Демографія
    0.55
    gridx
    0.54
    Activations Density 0.388%

    No Known Activations