© 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. 7235
    Prev
    Next
    INDEX
    Explanations

    mentions of study design or limitations of study

    oai_token-act-pair · gemini-2.0-flash

    code identifiers

    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
     second
    -3.02
    second
    -2.78
    Second
    -2.72
     Second
    -2.61
    SECOND
    -2.44
     SECOND
    -2.44
     Secondly
    -2.16
    Secondly
    -2.13
     secondly
    -2.11
     deuxième
    -2.05
    POSITIVE LOGITS
    Personendaten
    0.77
     NgModule
    0.59
    曖昧さ回避
    0.57
    WebVitals
    0.54
    SerializedName
    0.51
    propTypes
    0.49
     Pingback
    0.49
    EndContext
    0.49
    ROLS
    0.48
    XmlEnum
    0.48
    Activations Density 1.864%

    No Known Activations