© 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. 8669
    Prev
    Next
    INDEX
    Explanations

    a combination of auxiliary verbs, prepositions, and action verbs that indicate actions or ongoing processes.

    oai_token-act-pair · gemini-2.0-flash

    Long, rambling text

    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
    slightly
    -0.78
     occasional
    -0.77
     Occasionally
    -0.77
    Slightly
    -0.72
     occasionally
    -0.72
     Several
    -0.71
    حوالہ
    -0.69
     slightly
    -0.69
    Several
    -0.69
     Slightly
    -0.69
    POSITIVE LOGITS
     combineReducers
    0.52
     FBref
    0.52
     Godfrey
    0.48
    aland
    0.47
     }}$}
    0.44
    serviceWorker
    0.43
    haya
    0.43
     lại
    0.43
    ')"
    0.43
     springfox
    0.43
    Activations Density 8.515%

    No Known Activations