© 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. 6915
    Prev
    Next
    INDEX
    Explanations

    content from internet forums or blog posts

    oai_token-act-pair · gemini-2.0-flash

    Product/webpage discussion

    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
    cill
    -0.40
    hsl
    -0.40
     todella
    -0.38
    Dort
    -0.36
    ph
    -0.35
    how
    -0.35
     nasel
    -0.35
     nakalista
    -0.35
    wied
    -0.35
    phi
    -0.34
    POSITIVE LOGITS
     is
    0.88
     InputDecoration
    0.86
     protoimpl
    0.80
    ValueStyle
    0.79
    EDEFAULT
    0.78
    хьтан
    0.76
     linkovi
    0.76
    UnsafeEnabled
    0.74
     unknownFields
    0.73
    msgTypes
    0.73
    Activations Density 11.471%

    No Known Activations