© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16004
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, especially cities within Australia.

    oai_token-act-pair · gemini-2.0-flash

    Melbourne

    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
     utafitiHapana
    -0.54
    MigrationBuilder
    -0.48
    ce
    -0.46
    样
    -0.44
    <bos>
    -0.41
    ions
    -0.40
    Ni
    -0.39
    RegressionTest
    -0.39
    cm
    -0.39
    WK
    -0.39
    POSITIVE LOGITS
     Anſ
    0.84
     purpoſe
    0.82
     myſelf
    0.78
    CloseOperation
    0.77
     becauſe
    0.77
     Majefty
    0.77
     diſt
    0.75
     Chriftian
    0.75
     ―――――
    0.74
     ſche
    0.73
    Activations Density 0.270%

    No Known Activations