© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3732
    Prev
    Next
    INDEX
    Explanations

    the word "all" and nearby words such as 'way','across' and 'the', suggesting it identifies phrases about inclusivity or paths together

    oai_token-act-pair · gemini-2.0-flash

    say "the" or "through"

    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
     समीक्षक
    -0.64
     đó
    -0.58
    twimg
    -0.58
    ofag
    -0.55
    ͝
    -0.55
    rawDesc
    -0.53
     NSCoder
    -0.52
    /*
    -0.52
    ⓧ
    -0.51
    dAtA
    -0.50
    POSITIVE LOGITS
    Referencies
    0.64
    Gambas
    0.58
     doInBackground
    0.55
     vägen
    0.55
    ]-'
    0.52
    TestBed
    0.52
     Савезне
    0.52
     jäsen
    0.51
    Enlaces
    0.51
    RTEX
    0.50
    Activations Density 1.086%

    No Known Activations