© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4965
    Prev
    Next
    INDEX
    Explanations

    text related to historical academic research papers or articles including titles, references, prepositions like "of," "in," "by," and years.

    oai_token-act-pair · gemini-2.0-flash

    Snippets of text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ,
    -0.70
    With
    -0.66
     And
    -0.59
    A
    -0.58
    And
    -0.58
    Of
    -0.57
    As
    -0.57
     Of
    -0.54
    For
    -0.53
     With
    -0.53
    POSITIVE LOGITS
     Their
    0.92
     fermés
    0.75
    __':
    0.74
     Its
    0.73
     Our
    0.69
    hoeddwyd
    0.68
     cérami
    0.68
     prêts
    0.68
     betweenstory
    0.67
    EndGlobalSection
    0.67
    Activations Density 13.020%

    No Known Activations