© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10419
    Prev
    Next
    INDEX
    Explanations

    text that discusses nightstands, especially focused on storage and small spaces.

    oai_token-act-pair · gemini-2.0-flash

    structured data entries

    np_token-act-pair-logits · gpt-4o-mini

    Storing things

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     estekak
    -0.59
    IFUL
    -0.57
    ibald
    -0.53
     насељу
    -0.53
    ScopeManager
    -0.53
     <>",
    -0.52
    Jeografia
    -0.52
    otheby
    -0.51
    inske
    -0.51
     démoc
    -0.50
    POSITIVE LOGITS
    OGND
    0.57
     clothes
    0.57
    __["
    0.56
     groceries
    0.55
     lenker
    0.53
    featureID
    0.53
     Normdatei
    0.52
     extra
    0.52
    nalité
    0.52
     EventArgs
    0.51
    Activations Density 3.425%

    No Known Activations