© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14673
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'K', often followed by hyphens and numbers

    oai_token-act-pair · gemini-2.0-flash

    K

    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
    __':
    -0.79
    rungsseite
    -0.68
    __':
    -0.66
    __":
    -0.65
    EndContext
    -0.63
    componentDid
    -0.59
     useCallback
    -0.59
     kasarigan
    -0.59
    httphttps
    -0.58
    الإنجليزية
    -0.57
    POSITIVE LOGITS
    monary
    0.49
    canyon
    0.44
     Sensi
    0.44
    InitVars
    0.44
     MenuView
    0.43
     mecha
    0.43
    ########.
    0.43
     esternos
    0.43
     Airways
    0.42
    SP
    0.42
    Activations Density 0.280%

    No Known Activations