© 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. 14804
    Prev
    Next
    INDEX
    Explanations

    words like 'down' or 'passes' and prepositions that usually follow verbs in English

    oai_token-act-pair · gemini-2.0-flash

    say "down"

    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
     Down
    -1.84
    Down
    -1.77
    DOWN
    -1.71
     DOWN
    -1.66
     up
    -1.64
    down
    -1.62
     Up
    -1.58
    Up
    -1.54
    up
    -1.52
    downs
    -1.48
    POSITIVE LOGITS
    OGND
    0.59
    Referências
    0.59
    minecraftforge
    0.57
    ształ
    0.52
    QApplication
    0.52
    ]")]
    0.50
    tagHelper
    0.49
    UnitTesting
    0.48
     done
    0.48
    Namara
    0.47
    Activations Density 1.185%

    No Known Activations