© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10654
    Prev
    Next
    INDEX
    Explanations

    technical concepts in electronics, chemistry, or medicine

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    x
    -0.54
    '
    -0.45
    od
    -0.42
     finally
    -0.42
    -
    -0.41
    ↵↵
    -0.40
    s
    -0.40
    (
    -0.40
    h
    -0.40
    ,
    -0.40
    POSITIVE LOGITS
    تقاوى
    1.20
    Personendaten
    1.12
    Autoritní
    1.09
    posedge
    1.03
    tagHelperRunner
    0.99
    Personensuche
    0.96
    存于互联网档案馆
    0.93
    enterOuterAlt
    0.91
    AddTagHelper
    0.90
    UserScript
    0.90
    Activations Density 0.758%

    No Known Activations