© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10456
    Prev
    Next
    INDEX
    Explanations

    words used in movie or video reviews when expressing opinions about the quality of what's on the screen or in the audio.

    oai_token-act-pair · gemini-2.0-flash

    Image quality/blurring

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     sociala
    -0.47
     sociais
    -0.45
    oznam
    -0.44
     Spagna
    -0.43
     Fifth
    -0.42
    var
    -0.42
    SafeMath
    -0.42
    TestRunner
    -0.41
     testemun
    -0.41
     Meksiku
    -0.40
    POSITIVE LOGITS
    GEBURTSDATUM
    0.89
    expandindo
    0.84
    UnsafeEnabled
    0.73
     createState
    0.71
     Réponses
    0.69
    AnchorStyles
    0.69
     Waray
    0.68
     المعيارى
    0.68
    }{*}{}
    0.66
    /**
    0.66
    Activations Density 6.725%

    No Known Activations