© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 13126
    Prev
    Next
    INDEX
    Explanations

    code snippets referencing object sizing

    oai_token-act-pair · gemini-2.0-flash

    equals size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    emus
    -0.56
     fubject
    -0.54
     kasarigan
    -0.51
    ureusement
    -0.50
    pédie
    -0.50
    cense
    -0.50
     Penrose
    -0.50
     itſelf
    -0.49
     auffi
    -0.49
    }";
    -0.48
    POSITIVE LOGITS
    +#+#
    0.88
    migrationBuilder
    0.71
     становника
    0.70
    VIAF
    0.66
    TemporalType
    0.66
    prepareStatement
    0.63
     BoxDecoration
    0.60
    LookAnd
    0.59
     ContentValues
    0.58
    PointerException
    0.57
    Activations Density 0.016%

    No Known Activations