© 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. 11790
    Prev
    Next
    INDEX
    Explanations

    words in the context of argumentative writing

    oai_token-act-pair · gemini-2.0-flash

    part

    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
    enumii
    -0.66
     StatefulWidget
    -0.63
     समीक्षाओं
    -0.59
    VIAF
    -0.54
    Попис
    -0.51
    tvguidetime
    -0.48
     AspNetCore
    -0.48
    tagHelperRunner
    -0.48
    itzenden
    -0.47
    rostis
    -0.46
    POSITIVE LOGITS
     part
    3.75
    part
    3.31
    Part
    3.00
     Part
    2.77
     parte
    2.42
     PART
    2.36
     parts
    2.16
    PART
    2.09
     Teil
    2.08
     часть
    1.94
    Activations Density 14.704%

    No Known Activations