© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11636
    Prev
    Next
    INDEX
    Explanations

    documentation related to tokens and the Slack API

    oai_token-act-pair · gemini-2.0-flash

    Authentication and APIs

    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
     MonoBehaviour
    -0.67
     IEnumerator
    -0.62
     viewDidLoad
    -0.58
    forName
    -0.57
    DispatchToProps
    -0.57
    ;#
    -0.57
    endforeach
    -0.56
     defaultstate
    -0.55
    GEBURTS
    -0.55
     pulumi
    -0.54
    POSITIVE LOGITS
    ThemeOverlay
    0.58
     sociala
    0.47
     spéciale
    0.46
     InputDecoration
    0.46
    acces
    0.45
     applau
    0.44
     Méditerranée
    0.44
    aute
    0.44
    withstanding
    0.43
     spéciaux
    0.43
    Activations Density 4.119%

    No Known Activations