© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16245
    Prev
    Next
    INDEX
    Explanations

    nouns and adjectives that relate to broad, miscellaneous topics.

    oai_token-act-pair · gemini-2.0-flash

    Like

    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
     such
    -1.43
    such
    -1.28
    Such
    -1.25
     Such
    -1.19
     SUCH
    -1.05
     solche
    -0.98
     solches
    -0.79
    ########.
    -0.79
     такую
    -0.77
     такого
    -0.75
    POSITIVE LOGITS
     like
    2.69
     Like
    2.09
    Like
    2.08
    like
    1.97
     LIKE
    1.90
    LIKE
    1.59
     seperti
    1.27
     như
    1.22
     wie
    1.15
     כמו
    1.13
    Activations Density 8.222%

    No Known Activations