© 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. 14986
    Prev
    Next
    INDEX
    Explanations

    geographic locations and descriptions of landscapes

    oai_token-act-pair · gemini-2.0-flash

    coastal locations

    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
     للمعارف
    -0.84
     estekak
    -0.78
     שוליים
    -0.76
    dymyr
    -0.75
     Autorizaciones
    -0.71
     يتيمه
    -0.69
    例句
    -0.68
     consultato
    -0.67
    +#+#
    -0.67
    Parcelize
    -0.65
    POSITIVE LOGITS
    Personendaten
    0.55
     lag
    0.45
     stil
    0.44
    ukone
    0.43
     ester
    0.39
    +"&
    0.39
     gyrus
    0.39
     Eust
    0.39
     stack
    0.38
    AndEndTag
    0.38
    Activations Density 1.471%

    No Known Activations