© 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. 14829
    Prev
    Next
    INDEX
    Explanations

    seemingly random uses of the number 6

    oai_token-act-pair · gemini-2.0-flash

    say "9"

    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
    is
    -0.54
    aris
    -0.53
     is
    -0.53
     Is
    -0.51
    ider
    -0.51
     Res
    -0.50
    ret
    -0.50
    asi
    -0.50
     us
    -0.49
    …”
    -0.49
    POSITIVE LOGITS
    extAlignment
    0.86
    SourceChecksum
    0.84
    DeleteBehavior
    0.82
    Sucesor
    0.78
    Autoritní
    0.72
    ształ
    0.70
    TagMode
    0.70
    VersionUID
    0.70
    Šaltiniai
    0.70
     Shakspeare
    0.69
    Activations Density 0.884%

    No Known Activations