© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11543
    Prev
    Next
    INDEX
    Explanations

    email addresses, code snippets, and other non-sentence structured text

    oai_token-act-pair · gemini-2.0-flash

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Diſ
    -0.60
    cemment
    -0.59
     another
    -0.58
     Majefty
    -0.56
     Reſ
    -0.56
     NoSuch
    -0.55
     Pingback
    -0.54
     leſs
    -0.53
     Houſe
    -0.52
     aforementioned
    -0.51
    POSITIVE LOGITS
    <bos>
    2.16
    '
    1.25
    ’
    1.02
     getItemId
    0.79
    ')))
    0.76
    verwijspagina
    0.71
    '")
    0.67
    ‘
    0.66
     disambiguazione
    0.66
    '))
    0.65
    Activations Density 7.470%

    No Known Activations