© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9579
    Prev
    Next
    INDEX
    Explanations

    mentions of ambition or hopes for the future

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "dream" and its variants

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

    dream

    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
    ScopeManager
    -0.63
     Geraadpleegd
    -0.60
     arşivlendi
    -0.59
    ]='\
    -0.58
    TintMode
    -0.54
    LookAnd
    -0.53
    WebServlet
    -0.53
    sonian
    -0.52
     $#
    -0.52
    TProtocol
    -0.51
    POSITIVE LOGITS
    +#+#
    0.57
    findpost
    0.51
    MemoryWarning
    0.49
    gez
    0.48
    ineno
    0.47
     came
    0.47
     elevación
    0.46
     îles
    0.45
    posisi
    0.45
    came
    0.45
    Activations Density 2.552%

    No Known Activations