© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 261
    Prev
    Next
    INDEX
    Explanations

    content-free words such as conjunctions, prepositions, pronouns, and punctuation within sentences

    oai_token-act-pair · gemini-2.0-flash

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    -
    -0.55
     financières
    -0.54
     at
    -0.53
     solches
    -0.53
    THIS
    -0.51
     alebo
    -0.51
     réguli
    -0.50
    <?=
    -0.50
     définiti
    -0.50
     suivante
    -0.49
    POSITIVE LOGITS
     among
    0.95
     AMONG
    0.89
     amongst
    0.84
    among
    0.83
     مشين
    0.75
     Among
    0.74
     resourceCulture
    0.66
     wśród
    0.65
    Among
    0.65
     Amongst
    0.63
    Activations Density 11.688%

    No Known Activations