© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11990
    Prev
    Next
    INDEX
    Explanations

    pronouns, articles and conjunctions in the text

    oai_token-act-pair · gemini-2.0-flash

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    zzleHttp
    -0.66
    +#+#
    -0.65
    bootstrapcdn
    -0.57
    RunWith
    -0.55
    Viited
    -0.54
     useSelector
    -0.53
     becoming
    -0.53
    ={`/
    -0.53
     TLV
    -0.51
     receiving
    -0.51
    POSITIVE LOGITS
     was
    1.49
    was
    1.27
    Was
    1.23
     Was
    1.21
     were
    1.16
     Were
    0.94
     было
    0.92
    were
    0.91
     была
    0.90
     WAS
    0.89
    Activations Density 2.705%

    No Known Activations