© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8155
    Prev
    Next
    INDEX
    Explanations

    code snippets, specifically related to configurations or parameters

    oai_token-act-pair · gemini-2.0-flash

    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_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
     himſelf
    -0.66
     Chriſt
    -0.64
     femei
    -0.60
     themſelves
    -0.60
     religieuse
    -0.60
     chaude
    -0.59
     décé
    -0.59
     africaine
    -0.58
     theſe
    -0.58
     sportivo
    -0.57
    POSITIVE LOGITS
    ">//
    0.74
     '{@
    0.69
    awtextra
    0.69
    ("")]
    
    0.68
    }],
    
    0.66
    )}{\
    0.66
    AccessorTable
    0.65
    }}}{\
    0.64
    providedIn
    0.63
    "])){
    0.62
    Activations Density 13.072%

    No Known Activations