© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13524
    Prev
    Next
    INDEX
    Explanations

    sentences where the narrator is talking about what they like

    oai_token-act-pair · gemini-2.0-flash

    expressed preferences/opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Carriera
    -0.91
    ValueStyle
    -0.86
    IndentedString
    -0.84
    InsertCommand
    -0.81
    addContainerGap
    -0.81
    oa̍t
    -0.81
    abestanden
    -0.79
    yntaxException
    -0.75
    rawDesc
    -0.75
    Portale
    -0.74
    POSITIVE LOGITS
     râ
    0.32
    war
    0.30
    em
    0.30
    류
    0.29
     fır
    0.29
     enro
    0.29
     practicing
    0.28
    ībā
    0.28
    р
    0.28
    beh
    0.27
    Activations Density 2.172%

    No Known Activations