© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9889
    Prev
    Next
    INDEX
    Explanations

    sentences where someone is making a point

    oai_token-act-pair · gemini-2.0-flash

    critical commentary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     failure
    -0.54
     fail
    -0.49
    FAIL
    -0.49
     chng
    -0.45
     Fail
    -0.45
     crack
    -0.44
    []{"
    -0.43
    Sapp
    -0.43
    对
    -0.42
     mistake
    -0.41
    POSITIVE LOGITS
    ftagPool
    0.86
    djangoproject
    0.77
    
    0.69
     صوتيه
    0.67
     createSlice
    0.66
    \{\\
    0.65
    MigrationBuilder
    0.65
     referrerpolicy
    0.63
    InitStruct
    0.63
     useAppContext
    0.62
    Activations Density 3.993%

    No Known Activations