Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1688
    Prev
    Next
    INDEX
    Explanations

    tokens indicative of locations on a map or in a hierarchy

    oai_token-act-pair · gemini-2.0-flash

    single digit numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -1.30
     myſelf
    -1.18
     Theſe
    -1.18
     '\\;'
    -1.06
     purpoſe
    -1.04
    ^(@)
    -1.04
     Monfieur
    -1.00
     itſelf
    -0.99
     صوتيه
    -0.97
     AssemblyCulture
    -0.96
    POSITIVE LOGITS
    2
    1.00
    4
    0.98
    3
    0.97
    1
    0.97
    5
    0.94
    6
    0.94
    8
    0.92
    7
    0.92
    ...
    0.90
    …
    0.87
    Activations Density 48.091%

    No Known Activations