© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14603
    Prev
    Next
    INDEX
    Explanations

    words related to software and coding, specifically related to files/folders

    oai_token-act-pair · gemini-2.0-flash

    technical problem solving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ומת
    -0.54
     Infórmanos
    -0.52
    <bos>
    -0.47
    Autoritní
    -0.46
    ായ
    -0.46
    ⁠
    -0.46
    [`
    -0.45
    UNDA
    -0.45
    tvguidetime
    -0.45
     Ver
    -0.45
    POSITIVE LOGITS
    LookAnd
    0.83
    DockStyle
    0.77
    expandindo
    0.68
     AssemblyProduct
    0.65
     насељу
    0.64
    }))
    0.62
    ########.
    0.61
     jScrollPane
    0.61
     numerus
    0.60
     "..\..\..\
    0.59
    Activations Density 5.489%

    No Known Activations