© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11084
    Prev
    Next
    INDEX
    Explanations

    information on the number of things (especially study sizes)

    oai_token-act-pair · gemini-2.0-flash

    Numbers in data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    الإنجليزية
    -0.78
     typelib
    -0.78
     forceps
    -0.70
     occafion
    -0.69
     ujednoznacz
    -0.69
    évaluateur
    -0.68
    Билгалдахарш
    -0.67
    олові
    -0.65
     AssemblyProduct
    -0.65
     purpoſe
    -0.65
    POSITIVE LOGITS
     ged
    0.45
    Bioaccumulative
    0.43
     hele
    0.43
     rég
    0.42
     Roskov
    0.41
    whole
    0.40
     solange
    0.40
     linkovi
    0.40
    iment
    0.40
    akura
    0.40
    Activations Density 3.074%

    No Known Activations