© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14905
    Prev
    Next
    INDEX
    Explanations

    French place names

    oai_token-act-pair · gemini-2.0-flash

    special terms or keywords related to French administrative divisions

    np_token-act-pair-logits · gpt-4o-mini

    European 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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Geplaatst
    -0.81
    ContentAsync
    -0.81
    rungsseite
    -0.68
     مرئيه
    -0.67
    SBATCH
    -0.65
    ьаж
    -0.60
     aussch
    -0.59
     myſelf
    -0.59
     canst
    -0.59
    IndentedString
    -0.59
    POSITIVE LOGITS
     estimés
    0.54
     AssemblyVersion
    0.47
    })()
    0.44
    lawayo
    0.44
    ClassPath
    0.44
    hiana
    0.43
     contado
    0.43
     salto
    0.43
    ళ్
    0.42
     Lin
    0.42
    Activations Density 0.781%

    No Known Activations