© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12032
    Prev
    Next
    INDEX
    Explanations

    references to "I/we/you" as a subject with positive verbs, reflecting personal sentiment.

    oai_token-act-pair · gemini-2.0-flash

    Positive sentiment/preferences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    CodedInputStream
    -0.86
    addContainerGap
    -0.82
     Amic
    -0.74
    DockStyle
    -0.72
    protoimpl
    -0.69
     preference
    -0.68
    OwnProperty
    -0.65
     beginnetje
    -0.65
     préfé
    -0.63
     Preference
    -0.62
    POSITIVE LOGITS
    (!__
    0.46
    ifrance
    0.42
     enjoy
    0.41
     naselje
    0.40
    IGENCE
    0.38
    gridx
    0.38
     fluxes
    0.37
    textAppearance
    0.37
     Napoléon
    0.37
    archie
    0.37
    Activations Density 1.944%

    No Known Activations