© 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. 4230
    Prev
    Next
    INDEX
    Explanations

    phrases about actions that someone could or should do

    oai_token-act-pair · gemini-2.0-flash

    actions and possibilities

    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
    SequentialGroup
    -0.68
    ValueStyle
    -0.63
     Roskov
    -0.60
    done
    -0.59
     resourceCulture
    -0.57
     CreateTagHelper
    -0.56
     ordres
    -0.55
     mourut
    -0.52
     Done
    -0.52
     препратки
    -0.52
    POSITIVE LOGITS
     tartalomajánló
    0.62
    AutoresizingMask
    0.58
    NgModule
    0.51
    ActionCreators
    0.49
     שוליים
    0.46
     (),
    0.46
    ANZA
    0.45
    mdl
    0.45
    >-->
    0.43
     NgModule
    0.43
    Activations Density 10.475%

    No Known Activations