© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3232
    Prev
    Next
    INDEX
    Explanations

    the parts of a software license

    oai_token-act-pair · gemini-2.0-flash

    say "The"

    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
    the
    -0.94
     the
    -0.84
     nationaux
    -0.62
     giapp
    -0.59
     την
    -0.58
     pobres
    -0.55
     sexuales
    -0.53
     sjø
    -0.52
     τις
    -0.52
     fédé
    -0.52
    POSITIVE LOGITS
     The
    1.22
     يتيمه
    0.56
    bibfield
    0.54
    The
    0.54
    rungsseite
    0.54
    stateMutability
    0.53
     виправивши
    0.52
     GenerationType
    0.52
    shadowOpacity
    0.51
    astify
    0.51
    Activations Density 2.339%

    No Known Activations