© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8842
    Prev
    Next
    INDEX
    Explanations

    the word "in", and words ending in "ram", "has", and "orum"

    oai_token-act-pair · gemini-2.0-flash

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    tehende
    -0.54
     hinaus
    -0.53
    PullParser
    -0.51
     handleChange
    -0.51
    หมือน
    -0.50
    }^{(\
    -0.49
    matter
    -0.49
    ToTensor
    -0.47
     lenker
    -0.47
    landır
    -0.47
    POSITIVE LOGITS
    <bos>
    0.93
    ⓧ
    0.69
    sizeCache
    0.62
    SourceChecksum
    0.61
     >=",
    0.58
     trajets
    0.56
    ifikant
    0.54
     calendriers
    0.54
    ")->
    0.54
     Its
    0.53
    Activations Density 0.060%

    No Known Activations