© 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. 3878
    Prev
    Next
    INDEX
    Explanations

    references to grade levels

    oai_token-act-pair · gemini-2.0-flash

    school grades

    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
    ècie
    -0.86
     esternos
    -0.84
    Према
    -0.82
    FormTagHelper
    -0.82
     autorytatywna
    -0.81
     protoimpl
    -0.79
     tartalomajánló
    -0.77
    migrationBuilder
    -0.77
     iNdEx
    -0.76
    PreferredItem
    -0.75
    POSITIVE LOGITS
    ars
    0.53
     iub
    0.53
    van
    0.41
    F
    0.41
    ut
    0.41
    om
    0.40
    ens
    0.40
    hon
    0.39
    V
    0.38
    ann
    0.38
    Activations Density 2.022%

    No Known Activations