© 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. 4132
    Prev
    Next
    INDEX
    Explanations

    the digit 8 but also other digits

    oai_token-act-pair · gemini-2.0-flash

    8

    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
    httphttps
    -0.62
    thâu
    -0.58
     CascadeType
    -0.57
    hemian
    -0.54
    ESAR
    -0.53
    strar
    -0.53
     հղումներ
    -0.53
    apult
    -0.52
    ecturer
    -0.52
    CodeAttribute
    -0.52
    POSITIVE LOGITS
    errHandler
    0.52
    +#+#
    0.50
    EndTag
    0.48
    busch
    0.44
    োগ
    0.43
     <>",
    0.41
     reductase
    0.40
    StructEnd
    0.40
    culable
    0.40
    apunov
    0.40
    Activations Density 4.893%

    No Known Activations