© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14492
    Prev
    Next
    INDEX
    Explanations

    dates and eras, especially from the past

    oai_token-act-pair · gemini-2.0-flash

    geological time periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     aras
    -0.48
     regards
    -0.46
    dova
    -0.43
    짖
    -0.42
    zana
    -0.42
    ENCIÓN
    -0.41
    ज्ञ
    -0.40
    nol
    -0.40
     vulga
    -0.40
    akses
    -0.39
    POSITIVE LOGITS
     صوتيه
    1.07
     незавершена
    1.01
     nakalista
    0.81
    Diweddarwch
    0.80
    #+#
    0.75
     للمعارف
    0.73
    ArgsConstructor
    0.73
    SequentialGroup
    0.72
     snippetHide
    0.72
     propOrder
    0.71
    Activations Density 5.515%

    No Known Activations