© 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. 11851
    Prev
    Next
    INDEX
    Explanations

    references to scientific publications including journal names, numbers, and author names

    oai_token-act-pair · gemini-2.0-flash

    Astronomy

    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
     encom
    -0.44
    ornment
    -0.44
    pez
    -0.43
    atr
    -0.42
     Rit
    -0.40
     Each
    -0.40
    地上
    -0.40
    olyte
    -0.39
    Gn
    -0.39
    nexus
    -0.39
    POSITIVE LOGITS
     '\\;'
    0.95
    AndEndTag
    0.93
    ⓧ
    0.86
    TagMode
    0.85
     Roskov
    0.84
    bewerken
    0.81
    Jereo
    0.81
    InSection
    0.81
    AnchorStyles
    0.78
    featureID
    0.73
    Activations Density 1.207%

    No Known Activations