© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2540
    Prev
    Next
    INDEX
    Explanations

    instructions about cleaning something, especially with alcohol

    oai_token-act-pair · gemini-2.0-flash

    Technical, cleaning, and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    casting
    -0.81
     casting
    -0.78
     mould
    -0.74
     casts
    -0.72
     castings
    -0.71
     mold
    -0.70
    cast
    -0.68
     Casting
    -0.68
     moulds
    -0.66
    Mold
    -0.65
    POSITIVE LOGITS
    SequentialGroup
    0.58
     protoimpl
    0.57
    kloped
    0.56
    AÇÃO
    0.54
    }")]
    0.53
     Brush
    0.51
     kyr
    0.51
    tagext
    0.50
     propOrder
    0.50
    devamını
    0.50
    Activations Density 0.669%

    No Known Activations