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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11077
    Prev
    Next
    INDEX
    Explanations

    the word 'fall' followed by prepositions, and verbs like comply and rising

    oai_token-act-pair · gemini-2.0-flash

    fall/rise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -0.72
     calldata
    -0.55
    )]$
    -0.53
     اگه
    -0.51
    KommentareTeilen
    -0.50
     Morten
    -0.49
     hiszen
    -0.49
     دیگه
    -0.48
    μως
    -0.47
    商品説明
    -0.47
    POSITIVE LOGITS
    +#+#
    0.65
     AssemblyCulture
    0.65
     Normdatei
    0.64
    findpost
    0.64
     كومونز
    0.63
     onOptions
    0.63
     ErrIntOverflow
    0.62
    󠁢
    0.61
     BrowserModule
    0.60
    digans
    0.60
    Activations Density 3.002%

    No Known Activations