© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9321
    Prev
    Next
    INDEX
    Explanations

    words and phrases used to describe personal preferences

    oai_token-act-pair · gemini-2.0-flash

    content related to personal interests and relationships

    np_token-act-pair-logits · gpt-4o-mini

    hobbies and interests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    mbro
    -0.48
    そこは
    -0.45
    its
    -0.44
     eingel
    -0.43
     vivido
    -0.43
     défaite
    -0.43
    ited
    -0.43
     revés
    -0.42
     üzere
    -0.41
     faveur
    -0.41
    POSITIVE LOGITS
     autorytatywna
    0.96
    GEBURTSDATUM
    0.94
    enumi
    0.90
    Personensuche
    0.84
    +#+#
    0.82
    MigrationBuilder
    0.82
    出版年
    0.81
    AddTagHelper
    0.81
    IsMutable
    0.80
    ⓧ
    0.77
    Activations Density 2.645%

    No Known Activations