© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1395
    Prev
    Next
    INDEX
    Explanations

    sentences that refer to the context of leadership and specific people in the story.

    oai_token-act-pair · gemini-2.0-flash

    job positions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    KURZBESCHREIBUNG
    -0.54
     propOrder
    -0.54
    Carcinogenicity
    -0.51
    angliski
    -0.47
     Grimal
    -0.46
    AttributeSet
    -0.45
     Sigism
    -0.45
    XtraReports
    -0.45
    μφωνα
    -0.45
    LOYE
    -0.44
    POSITIVE LOGITS
    ValueStyle
    0.90
     للاسماء
    0.68
    UnknownFieldSet
    0.66
     vícti
    0.66
     numé
    0.63
     plastiques
    0.62
     réguli
    0.61
     <<<<<<<<<<<<<<
    0.60
    contentLoaded
    0.59
     âgées
    0.59
    Activations Density 3.152%

    No Known Activations