© 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. 6807
    Prev
    Next
    INDEX
    Explanations

    text about a Christian education and defending the faith

    oai_token-act-pair · gemini-2.0-flash

    Mixed religious/political themes

    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
    IntoConstraints
    -0.82
     myſelf
    -0.79
     Chriftian
    -0.73
     itſelf
    -0.70
    TestingModule
    -0.69
     AssemblyCulture
    -0.69
     ModelExpression
    -0.68
     Jefus
    -0.66
    .*")]
    -0.65
     ſp
    -0.63
    POSITIVE LOGITS
    UnsafeEnabled
    0.50
     gynhyrchwyd
    0.49
    losis
    0.46
     witness
    0.45
    Witness
    0.44
    l
    0.44
     produisons
    0.44
     Shee
    0.44
     hộ
    0.44
    зь
    0.43
    Activations Density 6.264%

    No Known Activations